AI Models

313 models · 36 new in 60d

Compare →
Sort
NewestA→Z
Type
AllFlagshipSmallReasoningCodeEmbeddingImageVideoVisionAudiofunction-callinglocal AImultimodal
License
AllOpenClosed
  • DeepSeek V4 Pro 0813NewOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (446 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Pro-0813")

    transformerssafetensorsdeepseek_v4text-generationconversational

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813

    Auto-discovered from HuggingFace trending. 446 likes, 245 downloads.

  • NVIDIA Nemotron 3.5 Lightning 30B A3B NVFP4NewOpen

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (260 likes this week)

    How: Available on Hugging Face. 120K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4")

    transformerssafetensorsnemotron_htext-generationnvidia

    API: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4

    Auto-discovered from HuggingFace trending. 260 likes, 120K downloads.

  • Qwen3.8 2.4T A95BNewOpen

    Qwen · self-host

    ▾

    Best for: Trending on HuggingFace (930 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.8-2.4T-A95B")

    transformerssafetensorsqwen3_5_moe_texttext-generationconversational

    API: huggingface.co/Qwen/Qwen3.8-2.4T-A95B

    Auto-discovered from HuggingFace trending. 930 likes, 4K downloads.

  • LFM2.5 2.6B GGUFNewOpen

    LiquidAI · self-host

    ▾

    Best for: Trending on HuggingFace (176 likes this week)

    How: Available on Hugging Face. 68K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-2.6B-GGUF")

    ggufliquidlfm2.5llama.cpptext-generation

    API: huggingface.co/LiquidAI/LFM2.5-2.6B-GGUF

    Auto-discovered from HuggingFace trending. 176 likes, 68K downloads.

  • Ling 3.0 FlashNewOpen

    inclusionAI · self-host

    ▾

    Best for: Trending on HuggingFace (308 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-3.0-flash")

    safetensorsbailing_hybridtext-generationconversationalcustom_code

    API: huggingface.co/inclusionAI/Ling-3.0-flash

    Auto-discovered from HuggingFace trending. 308 likes, 6K downloads.

  • Maple PreviewNewOpen

    deepgrove · self-host

    ▾

    Best for: Trending on HuggingFace (337 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepgrove/maple-preview")

    transformerssafetensorstext-generationcausal-lmmixture-of-experts

    API: huggingface.co/deepgrove/maple-preview

    Auto-discovered from HuggingFace trending. 337 likes, 2K downloads.

  • XYZ Aquila ProNewOpen

    XYZAILab · self-host

    ▾

    Best for: Trending on HuggingFace (361 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("XYZAILab/XYZ-Aquila-pro")

    transformerssafetensorsqwen3_5_moeimage-text-to-textagentic-search

    API: huggingface.co/XYZAILab/XYZ-Aquila-pro

    Auto-discovered from HuggingFace trending. 361 likes, 1K downloads.

  • LFM2.5 2.6BNewOpen

    LiquidAI · self-host

    ▾

    Best for: Trending on HuggingFace (619 likes this week)

    How: Available on Hugging Face. 124K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-2.6B")

    transformerssafetensorslfm2text-generationliquid

    API: huggingface.co/LiquidAI/LFM2.5-2.6B

    Auto-discovered from HuggingFace trending. 619 likes, 124K downloads.

  • Qwen3.6 35B A3B Escha W2NewOpen

    EschaLabs · self-host

    ▾

    Best for: Trending on HuggingFace (210 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("EschaLabs/Qwen3.6-35B-A3B-Escha-W2")

    safetensorsqwen3_5_moemixture-of-expertsmoeqwen3

    API: huggingface.co/EschaLabs/Qwen3.6-35B-A3B-Escha-W2

    Auto-discovered from HuggingFace trending. 210 likes, 3K downloads.

  • XYZ Aquila MiniNewOpen

    XYZAILab · self-host

    ▾

    Best for: Trending on HuggingFace (417 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("XYZAILab/XYZ-Aquila-mini")

    transformerssafetensorsqwen3_5_moeimage-text-to-textqwen3.6

    API: huggingface.co/XYZAILab/XYZ-Aquila-mini

    Auto-discovered from HuggingFace trending. 417 likes, 1K downloads.

  • DeepSeek V4 Flash 0731NewOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (3393 likes this week)

    How: Available on Hugging Face. 1606K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-0731")

    transformerssafetensorsdeepseek_v4text-generationconversational

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731

    Auto-discovered from HuggingFace trending. 3393 likes, 1.6M downloads.

  • Solar Open2 250B Nota NVFP4NewOpen

    nota-ai · self-host

    ▾

    Best for: Trending on HuggingFace (151 likes this week)

    How: Available on Hugging Face. 19K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nota-ai/Solar-Open2-250B-Nota-NVFP4")

    vllmsafetensorssolar_open2quantizationnvfp4

    API: huggingface.co/nota-ai/Solar-Open2-250B-Nota-NVFP4

    Auto-discovered from HuggingFace trending. 151 likes, 19K downloads.

  • Claude Opus 5New

    Anthropic · 1M tokens · →

    ▾

    Best for: For complex agentic coding and enterprise work

    How: client.messages.create({model: "claude-opus-5", messages: [...]})

    Example: Use via the Anthropic SDK with model='claude-opus-5'.

    1M tokens contextadaptive thinking128k tokens max outputagentic coding

    API: api.anthropic.com — model: claude-opus-5 · AWS Bedrock · GCP Vertex AI

    Max output: 128k tokens. Adaptive thinking enabled by default.

  • KAT Coder V2.5 DevNewOpen

    Kwaipilot · self-host

    ▾

    Best for: Trending on HuggingFace (522 likes this week)

    How: Available on Hugging Face. 17K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Kwaipilot/KAT-Coder-V2.5-Dev")

    transformerssafetensorsqwen3_5_moeimage-text-to-textcode

    API: huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev

    Auto-discovered from HuggingFace trending. 522 likes, 17K downloads.

  • Antares 1bNewOpen

    fdtn-ai · self-host

    ▾

    Best for: Trending on HuggingFace (234 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("fdtn-ai/antares-1b")

    transformerssafetensorsgranitemoehybridtext-generationsecurity

    API: huggingface.co/fdtn-ai/antares-1b

    Auto-discovered from HuggingFace trending. 234 likes, 8K downloads.

  • Laguna S 2.1 NVFP4NewOpen

    poolside · self-host

    ▾

    Best for: Trending on HuggingFace (150 likes this week)

    How: Available on Hugging Face. 158K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-S-2.1-NVFP4")

    vllmsafetensorslagunalaguna-s-2.1text-generation

    API: huggingface.co/poolside/Laguna-S-2.1-NVFP4

    Auto-discovered from HuggingFace trending. 150 likes, 158K downloads.

  • Laguna S 2.1 GGUFNewOpen

    unsloth · self-host

    ▾

    Best for: Trending on HuggingFace (249 likes this week)

    How: Available on Hugging Face. 130K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("unsloth/Laguna-S-2.1-GGUF")

    transformersgguflaguna-s-2.1unslothvllm

    API: huggingface.co/unsloth/Laguna-S-2.1-GGUF

    Auto-discovered from HuggingFace trending. 249 likes, 130K downloads.

  • Solar Open2 250BNewOpen

    upstage · self-host

    ▾

    Best for: Trending on HuggingFace (718 likes this week)

    How: Available on Hugging Face. 13K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("upstage/Solar-Open2-250B")

    transformerssafetensorssolar_open2text-generationupstage

    API: huggingface.co/upstage/Solar-Open2-250B

    Auto-discovered from HuggingFace trending. 718 likes, 13K downloads.

  • Nanbeige4.2 3BNewOpen

    Nanbeige · self-host

    ▾

    Best for: Trending on HuggingFace (652 likes this week)

    How: Available on Hugging Face. 35K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Nanbeige/Nanbeige4.2-3B")

    transformerssafetensorsnanbeigetext-generationllm

    API: huggingface.co/Nanbeige/Nanbeige4.2-3B

    Auto-discovered from HuggingFace trending. 652 likes, 35K downloads.

  • Motif 3 BetaNewOpen

    Motif-Technologies · self-host

    ▾

    Best for: Trending on HuggingFace (201 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Motif-Technologies/Motif-3-Beta")

    transformerssafetensorsMotiffeature-extractionmotif

    API: huggingface.co/Motif-Technologies/Motif-3-Beta

    Auto-discovered from HuggingFace trending. 201 likes, 3K downloads.

  • Laguna S 2.1NewOpen

    poolside · self-host

    ▾

    Best for: Trending on HuggingFace (910 likes this week)

    How: Available on Hugging Face. 82K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-S-2.1")

    transformerssafetensorslagunatext-generationlaguna-s-2.1

    API: huggingface.co/poolside/Laguna-S-2.1

    Auto-discovered from HuggingFace trending. 910 likes, 82K downloads.

  • Ternary Bonsai 27B Mlx 2bitNewOpen

    prism-ml · self-host

    ▾

    Best for: Trending on HuggingFace (131 likes this week)

    How: Available on Hugging Face. 18K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("prism-ml/Ternary-Bonsai-27B-mlx-2bit")

    mlxsafetensorsqwen3_5conversationalternary

    API: huggingface.co/prism-ml/Ternary-Bonsai-27B-mlx-2bit

    Auto-discovered from HuggingFace trending. 131 likes, 18K downloads.

  • MiniCPM5 1B Claude Opus Fable5 V2 Thinking GGUFNewOpen

    GnLOLot · self-host

    ▾

    Best for: Trending on HuggingFace (147 likes this week)

    How: Available on Hugging Face. 52K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF")

    ggufllama.cppquantizedminicpm5thinking

    API: huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking-GGUF

    Auto-discovered from HuggingFace trending. 147 likes, 52K downloads.

  • Bonsai 27B Mlx 1bitNewOpen

    prism-ml · self-host

    ▾

    Best for: Trending on HuggingFace (162 likes this week)

    How: Available on Hugging Face. 25K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("prism-ml/Bonsai-27B-mlx-1bit")

    mlxsafetensorsqwen3_5conversational1-bit

    API: huggingface.co/prism-ml/Bonsai-27B-mlx-1bit

    Auto-discovered from HuggingFace trending. 162 likes, 25K downloads.

  • MiniCPM5 1B Claude Opus Fable5 ThinkingNewOpen

    GnLOLot · self-host

    ▾

    Best for: Trending on HuggingFace (159 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking")

    transformerssafetensorsllamatext-generationminicpm

    API: huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking

    Auto-discovered from HuggingFace trending. 159 likes, 5K downloads.

  • Qwythos 9B V2NewOpen

    empero-ai · self-host

    ▾

    Best for: Trending on HuggingFace (138 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("empero-ai/Qwythos-9B-v2")

    transformerssafetensorsqwen3_5image-text-to-textqwythos

    API: huggingface.co/empero-ai/Qwythos-9B-v2

    Auto-discovered from HuggingFace trending. 138 likes, 8K downloads.

  • Bonsai 27B GgufNewOpen

    prism-ml · self-host

    ▾

    Best for: Trending on HuggingFace (654 likes this week)

    How: Available on Hugging Face. 2187K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("prism-ml/Bonsai-27B-gguf")

    llama.cppggufconversational1-bitllama-cpp

    API: huggingface.co/prism-ml/Bonsai-27B-gguf

    Auto-discovered from HuggingFace trending. 654 likes, 2.2M downloads.

  • Ternary Bonsai 27B GgufNewOpen

    prism-ml · self-host

    ▾

    Best for: Trending on HuggingFace (1101 likes this week)

    How: Available on Hugging Face. 665K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("prism-ml/Ternary-Bonsai-27B-gguf")

    llama.cppggufconversationalternary2-bit

    API: huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf

    Auto-discovered from HuggingFace trending. 1101 likes, 665K downloads.

  • Supra Router 51MNewOpen

    SupraLabs · self-host

    ▾

    Best for: Trending on HuggingFace (102 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-Router-51M")

    transformerssafetensorsllamatext-generationrouter

    API: huggingface.co/SupraLabs/Supra-Router-51M

    Auto-discovered from HuggingFace trending. 102 likes, 1K downloads.

  • Nemotron Labs Audex 30B A3BNewOpen

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (144 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Labs-Audex-30B-A3B")

    transformerssafetensorsnemotron_labs_audexnvidianemotron-labs-audex

    API: huggingface.co/nvidia/Nemotron-Labs-Audex-30B-A3B

    Auto-discovered from HuggingFace trending. 144 likes, 1K downloads.

  • Claude Opus 4.7

    Anthropic · 1M tokens · $5/M → $25/M

    ▾

    Best for: Most capable generally available model. Complex multi-step coding, long agentic workflows, 1M-token codebase reads.

    How: client.messages.create(model='claude-opus-4-7', ...). Adaptive thinking is on by default — no separate extended-thinking mode needed.

    Example: Use Claude Code CLI with --model claude-opus-4-7 to handle PR-sized refactors end-to-end in a single run.

    SWE-bench step-change over Opus 4.6Context 1M (~555k words)
    agentic codingnew tokenizeradaptive thinking1M context128k max output

    API: api.anthropic.com (model: claude-opus-4-7) · AWS Bedrock · GCP Vertex AI · Microsoft Foundry

    Step-change improvement in agentic coding vs Opus 4.6. New tokenizer means 1M tokens ≈ 555k words (vs 750k for Sonnet 4.6).

  • Gemma 4 31B DenseOpen

    Google · 256K tokens · self-host

    ▾

    Best for: Self-hosted multimodal production, commercial use, multilingual apps

    How: Dense 31B — fits on a single A100 or 2x RTX 4090. Apache 2.0 = fully commercial. Supports images and video natively.

    Example: Deploy as a private multimodal assistant that reads screenshots, logs, and video clips.

    LMSYS Arena #3 textMMLU ~82%
    multimodalimages + video35+ languagesApache 2.0dense architecture
    Hardware to self-host
    VRAM: 20GB (quantized) / 62GB (FP16)
    GPU: 1× A100 80GB or 2× RTX 4090 24GB
    RAM: 32GB+ system RAM

    31B dense. Native multimodal (images + video) increases compute cost vs text-only.

    API: Ollama, vLLM, Hugging Face, Vertex AI. ollama run gemma4:31b

    Brand new (Apr 2026). Ranked #3 on LMSYS Arena text leaderboard at launch.

  • DeepSeek V3.2Open

    DeepSeek · 164K tokens · self-host

    ▾

    Best for: Long-context coding, upgraded V3 deployments

    How: Drop-in upgrade from V3. Uses Dynamic Sparse Attention for better long-context performance.

    Example: Feed your entire microservice codebase and get cross-service dependency analysis.

    HumanEval 94.0%
    codingmathsparse attention (DSA)MIT licenseimproved context
    Hardware to self-host
    VRAM: 350GB (quantized)
    GPU: 8× H100 80GB
    RAM: 512GB+ system RAM

    Same hardware footprint as V3 — 671B with sparse attention.

    API: api.deepseek.com OR self-host via vLLM. Same OpenAI-compatible API.

  • Mistral Large 3Open

    Mistral · 256K tokens · self-host

    ▾

    Best for: European deployments, agent workflows, long-context multilingual apps

    How: Major upgrade from Large 2. MoE architecture with 41B active params. Same API, just change model ID.

    Example: Build a multi-tool agent that queries DBs, calls APIs, and generates reports in 30+ languages.

    MoE 41B active / 675B totalmultilingualfunction calling256K context
    Hardware to self-host
    VRAM: 350GB (quantized)
    GPU: 8× H100 80GB
    RAM: 512GB+ system RAM

    675B MoE (41B active). Datacenter class — most users go via api.mistral.ai.

    API: api.mistral.ai OR self-host via vLLM. OpenAI-compatible.

  • Kimi K2.5

    Moonshot AI · 256K tokens · $0.55/M → $2.19/M

    ▾

    Best for: Budget alternative to flagship models, Chinese language tasks

    How: OpenAI SDK with base_url='https://api.moonshot.ai/v1'. WARNING: has implicit reasoning that eats max_tokens.

    Example: Use moonshot-v1-8k instead for structured JSON tasks — kimi-k2.5 wastes tokens on hidden thinking.

    reasoningmultimodalcheap

    API: api.moonshot.ai — OpenAI-compatible

    Watch:hidden thinking burns tokenstemperature locked to 1
  • Claude Opus 4.6

    Anthropic · 1M tokens · $15/M → $75/M

    ▾

    Best for: Complex multi-step coding, large codebase refactors, long-document analysis

    How: Best via Claude Code CLI for coding tasks. For API: messages.create() with system prompt + tools.

    Example: claude-code: point it at a repo, describe the feature, it reads/edits/tests autonomously.

    SWE-bench 72.5%GPQA Diamond 74.9%HumanEval 95.4%
    reasoninglong contexttool useagentic workflowscode generation

    API: api.anthropic.com — SDK: pip install anthropic / npm i @anthropic-ai/sdk

  • Claude Sonnet 4.6

    Anthropic · 200K tokens · $3/M → $15/M

    ▾

    Best for: Production API backends, real-time chat, moderate complexity coding

    How: Drop-in replacement for Opus when you need faster/cheaper. Same API, just change model ID.

    Example: Use as the default model in your API gateway — upgrade to Opus only for hard problems.

    SWE-bench 65.2%HumanEval 93.8%
    speedcost-efficiencycodingtool use

    API: api.anthropic.com — same SDK as Opus

  • GPT-4.1

    OpenAI · 1M tokens · $2/M → $8/M

    ▾

    Best for: General-purpose API integration, multimodal apps, coding assistance

    How: client.chat.completions.create(model='gpt-4.1', messages=[...]). Supports vision, tools, JSON mode.

    Example: Build a PR review bot that reads diffs + screenshots and posts comments.

    SWE-bench 54.6%HumanEval 95.3%
    codinginstruction followinglong contextmultimodal

    API: api.openai.com — SDK: pip install openai / npm i openai

  • Llama 4 MaverickOpen

    Meta · 1M tokens · self-host

    ▾

    Best for: Self-hosted production deployments, privacy-sensitive workloads

    How: ollama run llama4-maverick OR deploy on vLLM with tensor parallelism. Also available hosted on Together/Groq.

    Example: Deploy on 2x A100 GPUs behind your API gateway for private code review.

    MMLU 88.4%HumanEval 84.8%
    multilingualmultimodalMoE architecture17B active / 400B total
    Hardware to self-host
    VRAM: 200GB (quantized)
    GPU: 2× H100 80GB or 4× A100 80GB
    RAM: 256GB system RAM

    400B total params (17B active). FP16 needs ~800GB, FP8 ~400GB, INT4 ~200GB.

    API: Self-host via vLLM, Ollama, or use via Together, Fireworks, Groq

  • Llama 4 ScoutOpen

    Meta · 10M tokens · self-host

    ▾

    Best for: Processing entire codebases, very long documents, single-GPU deployments

    How: Fits on a single H100. Best open model for extreme context lengths.

    Example: Feed your entire monorepo into context and ask about cross-service dependencies.

    MMLU 86.2%
    longest context (10M)MoE 17B active / 109B totalfits single H100
    Hardware to self-host
    VRAM: 80GB
    GPU: 1× H100 80GB
    RAM: 128GB system RAM

    17B active params, fits in a single H100 at FP8.

    API: Same as Maverick — vLLM, Ollama, Together, Fireworks

  • Qwen 3 235BOpen

    Alibaba · 128K tokens · self-host

    ▾

    Best for: Flexible thinking control, commercial self-hosting, multilingual

    How: Supports /think and /no_think tags to toggle reasoning on/off per request. Apache 2.0 = fully commercial.

    Example: Use /no_think for fast classification, /think for complex debugging — same model.

    AIME 2024 85.7%HumanEval 90.2%
    hybrid thinkingMoE 22B activeApache 2.0multilingual
    Hardware to self-host
    VRAM: 140GB (quantized)
    GPU: 4× A100 80GB or 2× H100
    RAM: 256GB+ system RAM

    235B total (22B active). MoE architecture — only 22B params active per forward pass.

    API: Self-host via vLLM/SGLang or use via Together, Fireworks. Also on Alibaba Cloud.

  • Gemini 2.5 Pro

    Google · 1M tokens · $1.25/M → $10/M

    ▾

    Best for: Long-document analysis, multimodal tasks, apps needing search grounding

    How: client.models.generate_content(model='gemini-2.5-pro', contents=[...]). Supports grounding with Google Search.

    Example: Feed a 200-page architecture doc and ask it to find security issues.

    SWE-bench 63.8%GPQA Diamond 67.2%
    multimodallong contextsearch groundingcode generation

    API: generativelanguage.googleapis.com — SDK: pip install google-genai

  • Grok 3

    xAI · 128K tokens · $3/M → $15/M

    ▾

    Best for: Tasks needing real-time information, math-heavy problems

    How: OpenAI SDK with base_url override. Also supports live search via tools.

    Example: Monitor real-time tech news and generate summaries using live search.

    GPQA Diamond 68.2%AIME 2024 93.3%
    reasoningreal-time datamath

    API: api.x.ai — OpenAI-compatible SDK. Set base_url='https://api.x.ai/v1'

  • Llama 3.3 70BOpen

    Meta · 128K tokens · self-host

    ▾

    Best for: Proven workhorse for self-hosted deployments, fine-tuning base

    How: ollama run llama3.3:70b. For production: vLLM on 2x A100 or 4x A10G.

    Example: Fine-tune on your internal docs for a private knowledge base chatbot.

    MMLU 86.0%HumanEval 88.4%
    mature ecosystemfine-tuning friendlywide hardware support
    Hardware to self-host
    VRAM: 40GB (4-bit) / 140GB (FP16)
    GPU: 2× A100 80GB or 4× A10G 24GB
    RAM: 64GB+ system RAM

    70B dense. Widely supported — runs on Ollama with quantization on 48GB VRAM.

    API: Ollama, vLLM, TGI, or hosted (Together $0.60/M, Groq, Fireworks)

  • DeepSeek V3Open

    DeepSeek · 128K tokens · self-host

    ▾

    Best for: Cost-sensitive production APIs, coding tasks, math-heavy pipelines

    How: Cheapest top-tier API. OpenAI-compatible. Self-host needs 8x A100.

    Example: Replace GPT-4 in your CI pipeline for automated code review at 1/10th the cost.

    HumanEval 92.1%MMLU 88.5%
    codingmathMoE 37B active / 671B totalMIT license
    Hardware to self-host
    VRAM: 350GB (quantized) / 1.3TB (FP16)
    GPU: 8× H100 80GB or 8× A100 80GB
    RAM: 512GB+ system RAM

    671B total (37B active). Most users rent via API — self-hosting needs datacenter hardware.

    API: api.deepseek.com ($0.27/M in, $1.10/M out) OR self-host

  • AMD GAIA

    AMD · 128K tokens · api

    ▾

    Best for: Email management and AI assistance

    How: Integrate GAIA with email clients for AI-powered email sorting and response generation

    Example: Use GAIA to automatically categorize incoming emails and suggest replies

    AI companion for emails

    Auto-discovered from news articles.

  • Lemonade 11.0

    AMD · N/A · api

    ▾

    Best for: Local AI server applications

    How: Integrate Lemonade 11.0 with AMD hardware for on-premises AI workloads

    Example: Use Lemonade 11.0 to deploy AI models leveraging AMD's CPUs, GPUs, and NPUs

    Text-to-speechSupport for AMD Ryzen CPUsSupport for AMD Radeon GPUsSupport for AMD Ryzen AI NPU

    Auto-discovered from news articles.

  • Hy3 GGUFNewOpen

    AngelSlim · self-host

    ▾

    Best for: Trending on HuggingFace (149 likes this week)

    How: Available on Hugging Face. 110K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("AngelSlim/Hy3-GGUF")

    gguftext-generationbase_model:tencent/Hy3base_model:quantized:tencent/Hy3license:apache-2.0

    API: huggingface.co/AngelSlim/Hy3-GGUF

    Auto-discovered from HuggingFace trending. 149 likes, 110K downloads.

  • LLM

    NVIDIA · 128K tokens · api

    ▾

    Best for: training large language models with reduced memory constraints

    How: employ Host Offloading technique during training

    Example: use NVIDIA's LLM training approach to mitigate GPU memory limits

    reduces high-bandwidth memory bottlenecksoptimized for JAX-based training

    Auto-discovered from news articles.

  • NVIDIA Nemotron Labs 3 Puzzle 75B A9B NVFP4Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (115 likes this week)

    How: Available on Hugging Face. 39K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4")

    transformerssafetensorsnemotron_h_puzzletext-generationnvidia

    API: huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4

    Auto-discovered from HuggingFace trending. 115 likes, 39K downloads.

  • GPT-5.6

    OpenAI · 128K tokens · api

    ▾

    Best for: high-level language tasks requiring deep understanding and generation

    How: use the API by calling `openai.Completion.create(model="gpt-5.6", prompt="your prompt here")`

    Example: Generate a summary of a long document or create a detailed response to a complex question

    state-of-the-art natural language processingadvanced understanding and generation capabilities

    Auto-discovered from news articles.

  • MiniCPM5 1B Claude Opus Fable5 Thinking GGUFNewOpen

    GnLOLot · self-host

    ▾

    Best for: Trending on HuggingFace (258 likes this week)

    How: Available on Hugging Face. 121K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF")

    ggufllama.cppquantizedminicpm5thinking

    API: huggingface.co/GnLOLot/MiniCPM5-1B-Claude-Opus-Fable5-Thinking-GGUF

    Auto-discovered from HuggingFace trending. 258 likes, 121K downloads.

  • LongCat 2.0NewOpen

    meituan-longcat · self-host

    ▾

    Best for: Trending on HuggingFace (183 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("meituan-longcat/LongCat-2.0")

    LongCat-2.0safetensorstransformerstext-generationconversational

    API: huggingface.co/meituan-longcat/LongCat-2.0

    Auto-discovered from HuggingFace trending. 183 likes, 2K downloads.

  • Hy3NewOpen

    tencent · self-host

    ▾

    Best for: Trending on HuggingFace (830 likes this week)

    How: Available on Hugging Face. 14K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("tencent/Hy3")

    transformerssafetensorshy_v3text-generationhunyuan

    API: huggingface.co/tencent/Hy3

    Auto-discovered from HuggingFace trending. 830 likes, 14K downloads.

  • D7VK 1.12Open

    Phoronix · 128K tokens · self-host

    ▾

    Best for: Optimizing Direct3D 7 and older applications on Linux

    How: Use D7VK 1.12 as the latest version of the implementation for Direct3D 7 and older atop the Vulkan API

    Example: Apply D7VK 1.12 to enhance the performance of legacy Direct3D applications on Linux systems

    Performance gains for older Direct3D versions on LinuxImplementation for Direct3D 7 and older atop the Vulkan API

    Auto-discovered from news articles.

  • Fable TracesNewOpen

    AliesTaha · self-host

    ▾

    Best for: Trending on HuggingFace (198 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("AliesTaha/fable-traces")

    transformerssafetensorsqwen3text-generationinstruct

    API: huggingface.co/AliesTaha/fable-traces

    Auto-discovered from HuggingFace trending. 198 likes, 5K downloads.

  • Claude Sonnet 5New

    Anthropic · 1M tokens · →

    ▾

    Best for: The best combination of speed and intelligence

    How: client.messages.create({model: "claude-sonnet-5", messages: [...]})

    Example: Use via the Anthropic SDK with model='claude-sonnet-5'.

    1M tokens contextadaptive thinking128k tokens max outputfast

    API: api.anthropic.com — model: claude-sonnet-5 · AWS Bedrock · GCP Vertex AI

    Max output: 128k tokens. Adaptive thinking enabled by default.

  • DeepSeek V4 Flash DSparkOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (144 likes this week)

    How: Available on Hugging Face. 33K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash-DSpark")

    transformerssafetensorsdeepseek_v4text-generationarxiv:2606.19348

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Flash-DSpark

    Auto-discovered from HuggingFace trending. 144 likes, 33K downloads.

  • Huihui GLM 5.2 Abliterated GGUFOpen

    huihui-ai · self-host

    ▾

    Best for: Trending on HuggingFace (180 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("huihui-ai/Huihui-GLM-5.2-abliterated-GGUF")

    transformersggufglm_moe_dsaunslothabliterated

    API: huggingface.co/huihui-ai/Huihui-GLM-5.2-abliterated-GGUF

    Auto-discovered from HuggingFace trending. 180 likes, 7K downloads.

  • Agents A1Open

    InternScience · self-host

    ▾

    Best for: Trending on HuggingFace (569 likes this week)

    How: Available on Hugging Face. 33K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("InternScience/Agents-A1")

    transformerssafetensorsqwen3_5_moeimage-text-to-textmoe

    API: huggingface.co/InternScience/Agents-A1

    Auto-discovered from HuggingFace trending. 569 likes, 33K downloads.

  • Qwen3.6 27B NVFP4Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (217 likes this week)

    How: Available on Hugging Face. 1713K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/Qwen3.6-27B-NVFP4")

    transformerssafetensorsqwen3_5image-text-to-textunsloth

    API: huggingface.co/nvidia/Qwen3.6-27B-NVFP4

    Auto-discovered from HuggingFace trending. 217 likes, 1.7M downloads.

  • LFM2.5 230MOpen

    LiquidAI · self-host

    ▾

    Best for: Trending on HuggingFace (182 likes this week)

    How: Available on Hugging Face. 22K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-230M")

    transformerssafetensorslfm2text-generationliquid

    API: huggingface.co/LiquidAI/LFM2.5-230M

    Auto-discovered from HuggingFace trending. 182 likes, 22K downloads.

  • Ornith 1.0 397BOpen

    deepreinforce-ai · self-host

    ▾

    Best for: Trending on HuggingFace (199 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-397B")

    transformerssafetensorsqwen3_5_moeimage-text-to-texttext-generation

    API: huggingface.co/deepreinforce-ai/Ornith-1.0-397B

    Auto-discovered from HuggingFace trending. 199 likes, 7K downloads.

  • GLM 5.2 NVFP4Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (210 likes this week)

    How: Available on Hugging Face. 160K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/GLM-5.2-NVFP4")

    Model Optimizersafetensorsglm_moe_dsanvidiaModelOpt

    API: huggingface.co/nvidia/GLM-5.2-NVFP4

    Auto-discovered from HuggingFace trending. 210 likes, 160K downloads.

  • DeepSeek V4 Pro DSparkOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (459 likes this week)

    How: Available on Hugging Face. 29K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Pro-DSpark")

    transformerssafetensorsdeepseek_v4text-generationarxiv:2606.19348

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Pro-DSpark

    Auto-discovered from HuggingFace trending. 459 likes, 29K downloads.

  • GPT‑5.6 Sol

    OpenAI · 128K tokens · api

    ▾

    Best for: advanced natural language processing tasks

    How: access the GPT-5.6 Sol model through the OpenAI API

    Example: use GPT-5.6 Sol for generating human-like text and summarization

    next-generation modelimproved capabilities over previous versions

    Auto-discovered from news articles.

  • GPT-5.6 Sol

    OpenAI · 128K tokens · api

    ▾

    Best for: advanced AI applications

    How: use GPT-5.6 Sol for cutting-edge AI tasks

    Example: deploy GPT-5.6 Sol for state-of-the-art AI applications

    next-generation model

    Auto-discovered from news articles.

  • Mythos AI

    Anthropic · 128K tokens · api

    ▾

    Best for: trusted AI applications

    How: deploy Mythos AI within trusted US organizations

    Example: use Mythos AI for secure and trusted AI applications

    trusted by US organizations

    Auto-discovered from news articles.

  • Ornith 1.0 9BOpen

    deepreinforce-ai · self-host

    ▾

    Best for: Trending on HuggingFace (385 likes this week)

    How: Available on Hugging Face. 76K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-9B")

    transformerssafetensorsqwen3_5image-text-to-texttext-generation

    API: huggingface.co/deepreinforce-ai/Ornith-1.0-9B

    Auto-discovered from HuggingFace trending. 385 likes, 76K downloads.

  • Ornith 1.0 35BOpen

    deepreinforce-ai · self-host

    ▾

    Best for: Trending on HuggingFace (343 likes this week)

    How: Available on Hugging Face. 225K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-35B")

    transformerssafetensorsqwen3_5_moeimage-text-to-texttext-generation

    API: huggingface.co/deepreinforce-ai/Ornith-1.0-35B

    Auto-discovered from HuggingFace trending. 343 likes, 225K downloads.

  • Ornith 1.0 9B GGUFOpen

    deepreinforce-ai · self-host

    ▾

    Best for: Trending on HuggingFace (455 likes this week)

    How: Available on Hugging Face. 455K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-9B-GGUF")

    transformersgguftext-generationlicense:mitendpoints_compatible

    API: huggingface.co/deepreinforce-ai/Ornith-1.0-9B-GGUF

    Auto-discovered from HuggingFace trending. 455 likes, 455K downloads.

  • Huihui Gemma 4 12B Coder Fable5 Composer2.5 V1 AbliteratedOpen

    huihui-ai · self-host

    ▾

    Best for: Trending on HuggingFace (127 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated")

    transformerssafetensorsgemma4_unifiedimage-text-to-textabliterated

    API: huggingface.co/huihui-ai/Huihui-gemma-4-12B-coder-fable5-composer2.5-v1-abliterated

    Auto-discovered from HuggingFace trending. 127 likes, 5K downloads.

  • Ornith 1.0 35B GGUFOpen

    deepreinforce-ai · self-host

    ▾

    Best for: Trending on HuggingFace (856 likes this week)

    How: Available on Hugging Face. 1347K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-35B-GGUF")

    transformersgguftext-generationlicense:mitendpoints_compatible

    API: huggingface.co/deepreinforce-ai/Ornith-1.0-35B-GGUF

    Auto-discovered from HuggingFace trending. 856 likes, 1.3M downloads.

  • Qwen AgentWorld 35B A3BOpen

    Qwen · self-host

    ▾

    Best for: Trending on HuggingFace (557 likes this week)

    How: Available on Hugging Face. 58K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-AgentWorld-35B-A3B")

    transformerssafetensorsqwen3_5_moeimage-text-to-textqwen

    API: huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B

    Auto-discovered from HuggingFace trending. 557 likes, 58K downloads.

  • GPT-5.5-Cyber

    OpenAI · 128K tokens · api

    ▾

    Best for: securing organizations by finding, validating, and patching vulnerabilities at scale

    How: Integrate GPT-5.5-Cyber with Daybreak tools to enhance security measures

    Example: Use GPT-5.5-Cyber to scan codebases for potential vulnerabilities and suggest patches

    vulnerability findingvalidationpatching

    Auto-discovered from news articles.

  • Qwythos 9B Claude Mythos 5 1MOpen

    empero-ai · self-host

    ▾

    Best for: Trending on HuggingFace (737 likes this week)

    How: Available on Hugging Face. 153K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("empero-ai/Qwythos-9B-Claude-Mythos-5-1M")

    transformerssafetensorsqwen3_5image-text-to-textqwen3.5

    API: huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M

    Auto-discovered from HuggingFace trending. 737 likes, 153K downloads.

  • Qwythos 9B Claude Mythos 5 1M GGUFOpen

    empero-ai · self-host

    ▾

    Best for: Trending on HuggingFace (2466 likes this week)

    How: Available on Hugging Face. 1571K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF")

    ggufllama.cppquantizedqwen3.5reasoning

    API: huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF

    Auto-discovered from HuggingFace trending. 2466 likes, 1.6M downloads.

  • ApertusOpen

    Open Foundation · 128K tokens · self-host

    ▾

    Best for: Suitable for users seeking an open and sovereign AI model.

    How: Integrate Apertus into your AI infrastructure to leverage its capabilities.

    Example: Use Apertus for natural language processing tasks requiring a high degree of sovereignty and transparency.

    Sovereign AIOpen Foundation Model

    Auto-discovered from news articles.

  • Qwen3.6 27B MTP Pi Tune GGUFOpen

    bytkim · self-host

    ▾

    Best for: Trending on HuggingFace (114 likes this week)

    How: Available on Hugging Face. 66K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("bytkim/Qwen3.6-27B-MTP-pi-tune-GGUF")

    ggufllama.cppqwenqwen3_6mtp

    API: huggingface.co/bytkim/Qwen3.6-27B-MTP-pi-tune-GGUF

    Auto-discovered from HuggingFace trending. 114 likes, 66K downloads.

  • Gemma 4 12B Agentic Fable5 Composer2.5 V2 3.5x Tau2 GGUFOpen

    yuxinlu1 · self-host

    ▾

    Best for: Trending on HuggingFace (1179 likes this week)

    How: Available on Hugging Face. 453K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF")

    ggufgemma4codingagenticterminal

    API: huggingface.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF

    Auto-discovered from HuggingFace trending. 1179 likes, 453K downloads.

  • GLM 5.2 FP8Open

    zai-org · self-host

    ▾

    Best for: Trending on HuggingFace (135 likes this week)

    How: Available on Hugging Face. 335K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.2-FP8")

    transformerssafetensorsglm_moe_dsatext-generationconversational

    API: huggingface.co/zai-org/GLM-5.2-FP8

    Auto-discovered from HuggingFace trending. 135 likes, 335K downloads.

  • Qwable V1Open

    lordx64 · self-host

    ▾

    Best for: Trending on HuggingFace (164 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("lordx64/Qwable-v1")

    transformerssafetensorsqwen3_5_moeimage-text-to-textqwen

    API: huggingface.co/lordx64/Qwable-v1

    Auto-discovered from HuggingFace trending. 164 likes, 4K downloads.

  • GLM 5.2 GGUFOpen

    unsloth · self-host

    ▾

    Best for: Trending on HuggingFace (487 likes this week)

    How: Available on Hugging Face. 180K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("unsloth/GLM-5.2-GGUF")

    ggufglm_moe_dsaunslothtext-generationen

    API: huggingface.co/unsloth/GLM-5.2-GGUF

    Auto-discovered from HuggingFace trending. 487 likes, 180K downloads.

  • Lemonade AI serverOpen

    AMD · N/A · self-host

    ▾

    Best for: cross-platform AI usage on Windows and Linux

    How: Integrate Lemonade AI server with MCP Server for enhanced capabilities

    Example: Use Lemonade AI server for private AI tasks on Windows and Linux systems

    100% free and private AI usageleverages AMD Ryzen AI NPUs, Radeon GPUs, and x86_64 CPUs

    Auto-discovered from news articles.

  • Lemonade AI ServerOpen

    AMD · 128K tokens · self-host

    ▾

    Best for: cross-platform AI usage on Windows and Linux

    How: install Lemonade AI server on Windows or Linux and start leveraging AI capabilities

    Example: use Lemonade AI server for on-device AI processing tasks

    100% free and private AI usageleverages AMD Ryzen AI NPUs, Radeon GPUs, and x86_64 CPUs

    Auto-discovered from news articles.

  • XR AI

    NVIDIA · 128K tokens · api

    ▾

    Best for: Creating AI experiences for AR glasses and wearable devices

    How: Integrate live data with AI models

    Example: Building AI agents for AR glasses and XR devices

    AI experiencesAR glasseswearable devices

    Auto-discovered from news articles.

  • Transaction Foundation Model

    NVIDIA · 128K tokens · api

    ▾

    Best for: Analyzing financial transaction data

    How: Use the Transaction Foundation Model to analyze transaction data

    Example: Understanding patterns of human behavior in financial transactions

    Analyzing transaction dataUnderstanding human behavior patterns

    Auto-discovered from news articles.

  • NVIDIA XR AI

    NVIDIA · 128K tokens · api

    ▾

    Best for: Developers building for AR glasses and wearable devices

    How: Integrate NVIDIA XR AI with AR glasses and wearable devices

    Example: Creating AI experiences for AR glasses and wearable devices

    AI experiences for AR glasses and wearable devicesIntegrates live data

    Auto-discovered from news articles.

  • VibeThinker 3BOpen

    WeiboAI · self-host

    ▾

    Best for: Trending on HuggingFace (744 likes this week)

    How: Available on Hugging Face. 59K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("WeiboAI/VibeThinker-3B")

    transformerssafetensorsqwen2text-generationmath

    API: huggingface.co/WeiboAI/VibeThinker-3B

    Auto-discovered from HuggingFace trending. 744 likes, 59K downloads.

  • GLM 5.2Open

    zai-org · self-host

    ▾

    Best for: Trending on HuggingFace (4894 likes this week)

    How: Available on Hugging Face. 2430K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.2")

    transformerssafetensorsglm_moe_dsatext-generationconversational

    API: huggingface.co/zai-org/GLM-5.2

    Auto-discovered from HuggingFace trending. 4894 likes, 2.4M downloads.

  • ESM2

    NVIDIA · 128K tokens · api

    ▾

    Best for: computational biology tasks

    How: Fine-tune ESM2 using NVIDIA BioNeMo recipes

    Example: Fine-tuning ESM2 with LoRA for specific protein tasks

    protein language understandinggenomic sequences

    Auto-discovered from news articles.

  • FastContext 1.0 4B SFTOpen

    microsoft · self-host

    ▾

    Best for: Trending on HuggingFace (356 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("microsoft/FastContext-1.0-4B-SFT")

    transformerssafetensorsqwen3text-generationExplorer SubAgent

    API: huggingface.co/microsoft/FastContext-1.0-4B-SFT

    Auto-discovered from HuggingFace trending. 356 likes, 6K downloads.

  • MiMo V2.5 Pro FP4 DFlashOpen

    XiaomiMiMo · self-host

    ▾

    Best for: Trending on HuggingFace (115 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash")

    transformerssafetensorsmimo_v2text-generationagent

    API: huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash

    Auto-discovered from HuggingFace trending. 115 likes, 4K downloads.

  • Gemma 4 12B Coder Fable5 Composer2.5 V1 GGUFOpen

    yuxinlu1 · self-host

    ▾

    Best for: Trending on HuggingFace (2596 likes this week)

    How: Available on Hugging Face. 641K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF")

    ggufgemma4codingcodereasoning

    API: huggingface.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF

    Auto-discovered from HuggingFace trending. 2596 likes, 641K downloads.

  • Ryzen AI Halo

    AMD · N/A · api

    ▾

    Best for: petite PC development

    How: work with either Microsoft Windows or Linux

    Example: use in AI development platforms

    Linux-friendlypowered by AMD Ryzen AI Max+

    Auto-discovered from news articles.

  • Claude Code

    Anthropic · 128K tokens · api

    ▾

    Best for: use in infrastructure management tasks

    How: connect AI to your infrastructure through the Model Context Protocol (MCP)

    Example: AI assistants like GitHub Copilot, IBM Bob, Claude Code etc. to interact with Terraform through the Model Context Protocol (MCP)

    interacts with Terraformsupports infrastructure management

    Auto-discovered from news articles.

  • DiffusionGemma

    NVIDIA · 128K tokens · api

    ▾

    Best for: real-time AI applications such as chat assistants, copilots, and agentic workflows

    How: Run DiffusionGemma on NVIDIA for high-throughput text generation

    Example: Developers can leverage DiffusionGemma for building real-time AI applications

    Developer-ReadyHigh-ThroughputText Generation

    Auto-discovered from news articles.

  • Nex N2 MiniOpen

    nex-agi · self-host

    ▾

    Best for: Trending on HuggingFace (220 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nex-agi/Nex-N2-mini")

    transformerssafetensorsqwen3_5_moeimage-text-to-texttext-generation

    API: huggingface.co/nex-agi/Nex-N2-mini

    Auto-discovered from HuggingFace trending. 220 likes, 8K downloads.

  • Claude Mythos 5

    Anthropic · 1M tokens · →

    ▾

    Best for: Available through Project Glasswing. Successor to Claude Mythos Preview.

    How: client.messages.create({model: "claude-mythos-5", messages: [...]})

    Example: Use via the Anthropic SDK with model='claude-mythos-5'.

    1M tokens contextadaptive thinking128k tokens max output

    API: api.anthropic.com — model: claude-mythos-5 · AWS Bedrock · GCP Vertex AI

    Max output: 128k tokens. Adaptive thinking enabled by default.

  • Claude Fable 5

    Anthropic · 1M tokens · →

    ▾

    Best for: Next-generation intelligence for long-running agents

    How: client.messages.create({model: "claude-fable-5", messages: [...]})

    Example: Use via the Anthropic SDK with model='claude-fable-5'.

    1M tokens contextadaptive thinking128k tokens max outputagentic coding

    API: api.anthropic.com — model: claude-fable-5 · AWS Bedrock · GCP Vertex AI

    Max output: 128k tokens. Adaptive thinking enabled by default.

  • Gemma 4 12B OBLITERATEDOpen

    OBLITERATUS · self-host

    ▾

    Best for: Trending on HuggingFace (336 likes this week)

    How: Available on Hugging Face. 76K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("OBLITERATUS/Gemma-4-12B-OBLITERATED")

    transformerssafetensorsggufgemma4_unifiedimage-text-to-text

    API: huggingface.co/OBLITERATUS/Gemma-4-12B-OBLITERATED

    Auto-discovered from HuggingFace trending. 336 likes, 76K downloads.

  • Nex N2 ProOpen

    nex-agi · self-host

    ▾

    Best for: Trending on HuggingFace (336 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nex-agi/Nex-N2-Pro")

    transformerssafetensorsqwen3_5_moeimage-text-to-texttext-generation

    API: huggingface.co/nex-agi/Nex-N2-Pro

    Auto-discovered from HuggingFace trending. 336 likes, 8K downloads.

  • North Mini Code 1.0Open

    CohereLabs · self-host

    ▾

    Best for: Trending on HuggingFace (475 likes this week)

    How: Available on Hugging Face. 20K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("CohereLabs/North-Mini-Code-1.0")

    transformerssafetensorscohere2_moetext-generationconversational

    API: huggingface.co/CohereLabs/North-Mini-Code-1.0

    Auto-discovered from HuggingFace trending. 475 likes, 20K downloads.

  • Google Gemini models

    Google · 128K tokens · api

    ▾

    Best for: AI applications

    How: integrate with Apple's new AI architecture

    Example: use in AI-powered applications

    AI architectureinnovative

    Auto-discovered from news articles.

  • NVIDIA Nemotron 3 Ultra 550B A55B NVFP4Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (160 likes this week)

    How: Available on Hugging Face. 91K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4")

    transformerssafetensorsnemotron_htext-generationnvidia

    API: huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4

    Auto-discovered from HuggingFace trending. 160 likes, 91K downloads.

  • Claude Opus 4.8

    Anthropic · 1M tokens · →

    ▾

    Best for: For complex agentic coding and enterprise work

    How: client.messages.create({model: "claude-opus-4-8", messages: [...]})

    Example: Use via the Anthropic SDK with model='claude-opus-4-8'.

    1M tokens contextadaptive thinking128k tokens max outputagentic coding

    API: api.anthropic.com — model: claude-opus-4-8 · AWS Bedrock · GCP Vertex AI

    Max output: 128k tokens. Adaptive thinking enabled by default.

  • NVIDIA Nemotron 3 Ultra 550B A55B BF16Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (189 likes this week)

    How: Available on Hugging Face. 59K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16")

    transformerssafetensorsnemotron_htext-generationnvidia

    API: huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16

    Auto-discovered from HuggingFace trending. 189 likes, 59K downloads.

  • Mellum2 12B A2.5B ThinkingOpen

    JetBrains · self-host

    ▾

    Best for: Trending on HuggingFace (274 likes this week)

    How: Available on Hugging Face. 18K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("JetBrains/Mellum2-12B-A2.5B-Thinking")

    transformerssafetensorsmellumtext-generationconversational

    API: huggingface.co/JetBrains/Mellum2-12B-A2.5B-Thinking

    Auto-discovered from HuggingFace trending. 274 likes, 18K downloads.

  • Qwen3.6 35B A3B NVFP4Open

    nvidia · self-host

    ▾

    Best for: Trending on HuggingFace (193 likes this week)

    How: Available on Hugging Face. 822K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("nvidia/Qwen3.6-35B-A3B-NVFP4")

    Model Optimizersafetensorsqwen3_5_moenvidiaModelOpt

    API: huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4

    Auto-discovered from HuggingFace trending. 193 likes, 822K downloads.

  • Mellum2

    JetBrains · api

    ▾

    Best for: Advanced AI tasks

    How: Integrate Mellum2 into your AI workflows

    Example: Use Mellum2 for complex problem-solving and decision-making

    12B Mixture-of-Experts Model

    Auto-discovered from news articles.

  • LFM2.5 8B A1B GGUFOpen

    LiquidAI · self-host

    ▾

    Best for: Trending on HuggingFace (177 likes this week)

    How: Available on Hugging Face. 87K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-8B-A1B-GGUF")

    ggufliquidlfm2edgellama.cpp

    API: huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF

    Auto-discovered from HuggingFace trending. 177 likes, 87K downloads.

  • Gemini 3.5

    Google · 128K tokens · api

    ▾

    Best for: General AI applications

    How: Integrate with Google I/O 2026

    Example: Watch 9 videos showing the capabilities of Gemini 3.5

    Advanced capabilitiesHigh performance

    Auto-discovered from news articles.

  • Gemini Omni

    Google · 128K tokens · api

    ▾

    Best for: General AI applications

    How: Integrate with Google I/O 2026

    Example: Watch 9 videos showing the capabilities of Gemini Omni

    Advanced capabilitiesHigh performance

    Auto-discovered from news articles.

  • Qwen3.6 27B OBLITERATEDOpen

    OBLITERATUS · self-host

    ▾

    Best for: Trending on HuggingFace (120 likes this week)

    How: Available on Hugging Face. 17K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("OBLITERATUS/Qwen3.6-27B-OBLITERATED")

    transformerssafetensorsggufqwen3_5_texttext-generation

    API: huggingface.co/OBLITERATUS/Qwen3.6-27B-OBLITERATED

    Auto-discovered from HuggingFace trending. 120 likes, 17K downloads.

  • LFM2.5 8B A1BOpen

    LiquidAI · self-host

    ▾

    Best for: Trending on HuggingFace (551 likes this week)

    How: Available on Hugging Face. 135K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-8B-A1B")

    transformerssafetensorslfm2_moetext-generationliquid

    API: huggingface.co/LiquidAI/LFM2.5-8B-A1B

    Auto-discovered from HuggingFace trending. 551 likes, 135K downloads.

  • Qwopus3.6 27B V2 MTP GGUFOpen

    Jackrong · self-host

    ▾

    Best for: Trending on HuggingFace (178 likes this week)

    How: Available on Hugging Face. 125K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Jackrong/Qwopus3.6-27B-v2-MTP-GGUF")

    transformersggufllama.cppimage-text-to-textvision

    API: huggingface.co/Jackrong/Qwopus3.6-27B-v2-MTP-GGUF

    Auto-discovered from HuggingFace trending. 178 likes, 125K downloads.

  • NVIDIA Blackwell

    NVIDIA · 128K tokens · api

    ▾

    Best for: financial trading landscape

    How: Enables sophisticated analysis

    Example: revolutionizing financial trading landscape

    sophisticated analysisvast amounts of unstructured data

    Auto-discovered from news articles.

  • ChatGPT

    OpenAI · 128K tokens · api

    ▾

    Best for: conversational AI and content generation in Portuguese

    How: Use ChatGPT API to integrate with applications

    Example: Generate news articles in Portuguese

    dialoguecontent creationinformation retrieval

    Auto-discovered from news articles.

  • MiniCPM5 1BOpen

    openbmb · self-host

    ▾

    Best for: Trending on HuggingFace (776 likes this week)

    How: Available on Hugging Face. 101K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B")

    transformerssafetensorsllamatext-generationminicpm

    API: huggingface.co/openbmb/MiniCPM5-1B

    Auto-discovered from HuggingFace trending. 776 likes, 101K downloads.

  • NVIDIA Cloud Partner (NCP) reference architecture

    NVIDIA · N/A · api

    ▾

    Best for: governments, enterprises, and telcos

    How: N/A

    Example: N/A

    sovereign AI factoriesbased on NCP reference architecture

    Auto-discovered from news articles.

  • Ring 2.6 1TOpen

    inclusionAI · self-host

    ▾

    Best for: Trending on HuggingFace (89 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ring-2.6-1T")

    transformerssafetensorsbailing_hybridtext-generationconversational

    API: huggingface.co/inclusionAI/Ring-2.6-1T

    Auto-discovered from HuggingFace trending. 89 likes, 3K downloads.

  • HRM Text 1BOpen

    sapientinc · self-host

    ▾

    Best for: Trending on HuggingFace (751 likes this week)

    How: Available on Hugging Face. 135K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("sapientinc/HRM-Text-1B")

    transformerssafetensorshrm_texttext-generationhrm

    API: huggingface.co/sapientinc/HRM-Text-1B

    Auto-discovered from HuggingFace trending. 751 likes, 135K downloads.

  • Deepseek V4 GgufOpen

    antirez · self-host

    ▾

    Best for: Trending on HuggingFace (139 likes this week)

    How: Available on Hugging Face. 284K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("antirez/deepseek-v4-gguf")

    ggufquantizeddeepseekdeepseek-v4deepseek-v4-flash

    API: huggingface.co/antirez/deepseek-v4-gguf

    Auto-discovered from HuggingFace trending. 139 likes, 284K downloads.

  • NVIDIA Vera Rubin Platform

    NVIDIA · 128K tokens · api

    ▾

    Best for: Agentic inference workloads

    How: Integrate with NVIDIA's platform for inference

    Example: Use for non-deterministic trajectories in AI

    Solving Agentic AI’s Scale-Up ProblemRuntime dynamics of inference workloads

    Auto-discovered from news articles.

  • NVIDIA Nemotron 3 Nano Omni 30B A3B Reasoning GGUFOpen

    unsloth · self-host

    ▾

    Best for: Trending on HuggingFace (100 likes this week)

    How: Available on Hugging Face. 45K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF")

    ggufnvidiaunslothnemotron-3multimodal

    API: huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

    Auto-discovered from HuggingFace trending. 100 likes, 45K downloads.

  • Ling 2.6 1TOpen

    inclusionAI · self-host

    ▾

    Best for: Trending on HuggingFace (111 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-2.6-1T")

    transformerssafetensorsbailing_hybridtext-generationconversational

    API: huggingface.co/inclusionAI/Ling-2.6-1T

    Auto-discovered from HuggingFace trending. 111 likes, 642 downloads.

  • Granite 4.1 30bOpen

    ibm-granite · self-host

    ▾

    Best for: Trending on HuggingFace (100 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.1-30b")

    transformerssafetensorsgranitetext-generationlanguage

    API: huggingface.co/ibm-granite/granite-4.1-30b

    Auto-discovered from HuggingFace trending. 100 likes, 6K downloads.

  • Granite 4.1 8bOpen

    ibm-granite · self-host

    ▾

    Best for: Trending on HuggingFace (157 likes this week)

    How: Available on Hugging Face. 20K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("ibm-granite/granite-4.1-8b")

    transformerssafetensorsgranitetext-generationlanguage

    API: huggingface.co/ibm-granite/granite-4.1-8b

    Auto-discovered from HuggingFace trending. 157 likes, 20K downloads.

  • Ling 2.6 FlashOpen

    inclusionAI · self-host

    ▾

    Best for: Trending on HuggingFace (456 likes this week)

    How: Available on Hugging Face.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ling-2.6-flash")

    safetensorsbailing_hybridtext-generationconversationalcustom_code

    API: huggingface.co/inclusionAI/Ling-2.6-flash

    Auto-discovered from HuggingFace trending. 456 likes, 1K downloads.

  • Laguna XS.2Open

    poolside · self-host

    ▾

    Best for: Trending on HuggingFace (228 likes this week)

    How: Available on Hugging Face. 14K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("poolside/Laguna-XS.2")

    transformerssafetensorslagunatext-generationlaguna-xs.2

    API: huggingface.co/poolside/Laguna-XS.2

    Auto-discovered from HuggingFace trending. 228 likes, 14K downloads.

  • Qwen3.6 27B DFlashOpen

    z-lab · self-host

    ▾

    Best for: Trending on HuggingFace (262 likes this week)

    How: Available on Hugging Face. 29K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("z-lab/Qwen3.6-27B-DFlash")

    transformerssafetensorsqwen3feature-extractiondflash

    API: huggingface.co/z-lab/Qwen3.6-27B-DFlash

    Auto-discovered from HuggingFace trending. 262 likes, 29K downloads.

  • Qwen3.6 35B A3B DFlashOpen

    z-lab · self-host

    ▾

    Best for: Trending on HuggingFace (165 likes this week)

    How: Available on Hugging Face. 27K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("z-lab/Qwen3.6-35B-A3B-DFlash")

    transformerssafetensorsqwen3feature-extractiondflash

    API: huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash

    Auto-discovered from HuggingFace trending. 165 likes, 27K downloads.

  • MiMo V2.5 ProOpen

    XiaomiMiMo · self-host

    ▾

    Best for: Trending on HuggingFace (506 likes this week)

    How: Available on Hugging Face. 40K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("XiaomiMiMo/MiMo-V2.5-Pro")

    safetensorsmimo_v2text-generationagentlong-context

    API: huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro

    Auto-discovered from HuggingFace trending. 506 likes, 40K downloads.

  • DeepSeek-V4-Flash

    DeepSeek · api

    ▾

    Best for: enabling highly efficient operations

    How: Build with DeepSeek V4 Using NVIDIA Blackwell and GPU-Accelerated Endpoints

    Example: DeepSeek just launched its fourth generation of flagship models

    highly efficient

    Auto-discovered from news articles.

  • DeepSeek-V4-Pro

    DeepSeek · api

    ▾

    Best for: enabling highly efficient operations

    How: Build with DeepSeek V4 Using NVIDIA Blackwell and GPU-Accelerated Endpoints

    Example: DeepSeek just launched its fourth generation of flagship models

    highly efficient

    Auto-discovered from news articles.

  • Hy3 PreviewOpen

    tencent · self-host

    ▾

    Best for: Trending on HuggingFace (189 likes this week)

    How: Available on Hugging Face. 14K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("tencent/Hy3-preview")

    transformerssafetensorshy_v3text-generationconversational

    API: huggingface.co/tencent/Hy3-preview

    Auto-discovered from HuggingFace trending. 189 likes, 14K downloads.

  • Google TPU 8th Generation

    Google · N/A · api

    ▾

    Best for: powering AI applications

    How: Deploy Google's 8th generation TPUs for your AI workloads

    Example: Use the new TPUs for training and inference in AI applications

    specialized chipsfuture of AI

    Auto-discovered from news articles.

  • Google TPUv8

    Google · N/A · api

    ▾

    Best for: AI acceleration

    How: deploy Google TPUv8 in your cloud environment

    Example: use Google TPUv8 for AI model training and inference

    specialized chipspower the future of AI

    Auto-discovered from news articles.

  • Google's 8th generation TPU

    Google AI · N/A · api

    ▾

    Best for: AI acceleration

    How: Deploy Google's 8th generation TPU for AI workloads.

    Example: Use the TPU for training and inference of AI models.

    specialized chipspower the future of AI

    Auto-discovered from news articles.

  • GPT-5.5

    OpenAI · 128K tokens · api

    ▾

    Best for: coding, research, and data analysis

    How: Integrate GPT-5.5 into your tools for advanced tasks.

    Example: Use GPT-5.5 for coding assistance or data analysis.

    fastermore capablecomplex tasks

    Auto-discovered from news articles.

  • DeepSeek V4 FlashOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (1948 likes this week)

    How: Available on Hugging Face. 2814K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Flash")

    transformerssafetensorsdeepseek_v4text-generationconversational

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Flash

    Auto-discovered from HuggingFace trending. 1948 likes, 2.8M downloads.

  • DeepSeek V4 ProOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (4999 likes this week)

    How: Available on Hugging Face. 2612K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4-Pro")

    transformerssafetensorsdeepseek_v4text-generationconversational

    API: huggingface.co/deepseek-ai/DeepSeek-V4-Pro

    Auto-discovered from HuggingFace trending. 4999 likes, 2.6M downloads.

  • Google's eighth generation TPU

    Google · N/A · api

    ▾

    Best for: AI applications requiring high-performance computing

    How: deploy on Google Cloud to leverage the new TPU capabilities

    Example: use for training and inference of large AI models

    powering the future of AItwo specialized chips

    Auto-discovered from news articles.

  • OpenAI Privacy Filter

    OpenAI · api

    ▾

    Best for: text privacy and compliance

    How: Integrate into text processing workflows

    Example: Automatically redact sensitive information from documents

    detecting and redacting PIIstate-of-the-art accuracy

    Auto-discovered from news articles.

  • Google's TPU (eighth generation)

    Google · api

    ▾

    Best for: AI acceleration

    How: Deploy in Google Cloud for AI tasks

    Example: Use for training and inference in AI applications

    specialized chipspower the future of AI

    Auto-discovered from news articles.

  • Qwen3.6 35B A3B Claude 4.6 Opus Reasoning Distilled GGUFOpen

    hesamation · self-host

    ▾

    Best for: Trending on HuggingFace (200 likes this week)

    How: Available on Hugging Face. 129K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF")

    ggufllama.cppqwenqwen3.6qwen3_5_moe

    API: huggingface.co/hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF

    Auto-discovered from HuggingFace trending. 200 likes, 129K downloads.

  • Qwopus GLM 18B Merged GGUFOpen

    Jackrong · self-host

    ▾

    Best for: Trending on HuggingFace (201 likes this week)

    How: Available on Hugging Face. 70K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Jackrong/Qwopus-GLM-18B-Merged-GGUF")

    ggufmergefrankenmergeqwen3.5reasoning

    API: huggingface.co/Jackrong/Qwopus-GLM-18B-Merged-GGUF

    Auto-discovered from HuggingFace trending. 201 likes, 70K downloads.

  • Gemma 4 31B It NVFP4 TurboOpen

    LilaRest · self-host

    ▾

    Best for: Trending on HuggingFace (247 likes this week)

    How: Available on Hugging Face. 105K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("LilaRest/gemma-4-31B-it-NVFP4-turbo")

    transformerssafetensorsgemma4text-generationgemma-4-31b-it

    API: huggingface.co/LilaRest/gemma-4-31B-it-NVFP4-turbo

    Auto-discovered from HuggingFace trending. 247 likes, 105K downloads.

  • Supergemma4 26b Uncensored Mlx 4bit V2Open

    Jiunsong · self-host

    ▾

    Best for: Trending on HuggingFace (172 likes this week)

    How: Available on Hugging Face. 14K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2")

    mlxsafetensorsgemma4uncensoredapple-silicon

    API: huggingface.co/Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2

    Auto-discovered from HuggingFace trending. 172 likes, 14K downloads.

  • Gemma 4 E4B It OBLITERATEDOpen

    OBLITERATUS · self-host

    ▾

    Best for: Trending on HuggingFace (526 likes this week)

    How: Available on Hugging Face. 128K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("OBLITERATUS/gemma-4-E4B-it-OBLITERATED")

    safetensorsggufgemma4abliterateduncensored

    API: huggingface.co/OBLITERATUS/gemma-4-E4B-it-OBLITERATED

    Auto-discovered from HuggingFace trending. 526 likes, 128K downloads.

  • Supergemma4 26b Uncensored Gguf V2Open

    Jiunsong · self-host

    ▾

    Best for: Trending on HuggingFace (627 likes this week)

    How: Available on Hugging Face. 267K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Jiunsong/supergemma4-26b-uncensored-gguf-v2")

    ggufgemma4uncensoredfastllama.cpp

    API: huggingface.co/Jiunsong/supergemma4-26b-uncensored-gguf-v2

    Auto-discovered from HuggingFace trending. 627 likes, 267K downloads.

  • GLM 5.1Open

    zai-org · self-host

    ▾

    Best for: Trending on HuggingFace (1472 likes this week)

    How: Available on Hugging Face. 171K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.1")

    transformerssafetensorsglm_moe_dsatext-generationconversational

    API: huggingface.co/zai-org/GLM-5.1

    Auto-discovered from HuggingFace trending. 1472 likes, 171K downloads.

  • MiniMax M2.7Open

    MiniMaxAI · self-host

    ▾

    Best for: Trending on HuggingFace (1052 likes this week)

    How: Available on Hugging Face. 469K downloads.

    Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2.7")

    transformerssafetensorsminimax_m2text-generationconversational

    API: huggingface.co/MiniMaxAI/MiniMax-M2.7

    Auto-discovered from HuggingFace trending. 1052 likes, 469K downloads.