AI Models

186 models · 22 new in 60d

Compare →
Sort
NewestA→Z
Type
AllFlagshipSmallReasoningCodeEmbeddingImageVideoVisionAudiofunction-callinglocal AImultimodal
License
AllOpenClosed
  • 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

  • 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 SFTNewOpen

    microsoft · self-host

    ▾

    Best for: Trending on HuggingFace (114 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. 114 likes, 13 downloads.

  • MiMo V2.5 Pro FP4 DFlashNewOpen

    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 GGUFNewOpen

    yuxinlu1 · self-host

    ▾

    Best for: Trending on HuggingFace (736 likes this week)

    How: Available on Hugging Face. 20K 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. 736 likes, 20K 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 MiniNewOpen

    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 5New

    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 5New

    Anthropic · 1M tokens · →

    ▾

    Best for: Anthropic's most capable widely released model, for the most demanding reasoning and long-horizon agentic work

    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 OBLITERATEDNewOpen

    OBLITERATUS · self-host

    ▾

    Best for: Trending on HuggingFace (326 likes this week)

    How: Available on Hugging Face. 71K 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. 326 likes, 71K downloads.

  • Nex N2 ProNewOpen

    nex-agi · self-host

    ▾

    Best for: Trending on HuggingFace (288 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. 288 likes, 4K downloads.

  • North Mini Code 1.0NewOpen

    CohereLabs · self-host

    ▾

    Best for: Trending on HuggingFace (394 likes this week)

    How: Available on Hugging Face. 11K 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. 394 likes, 11K downloads.

  • Google Gemini modelsNew

    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 NVFP4NewOpen

    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 4.8New

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

    ▾

    Best for: Anthropic's most capable Opus-tier model for complex reasoning and agentic coding

    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 BF16NewOpen

    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 ThinkingNewOpen

    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 NVFP4NewOpen

    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 GGUFNewOpen

    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 OBLITERATEDNewOpen

    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 A1BNewOpen

    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.

  • 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.

  • Qwopus3.6 27B V2 MTP GGUFNewOpen

    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.

  • 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 1BNewOpen

    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 1TNewOpen

    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 1BNewOpen

    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 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.

  • 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.

  • 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.

  • 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.

  • 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.

  • 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 (1371 likes this week)

    How: Available on Hugging Face. 3525K downloads.

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

    transformerssafetensorsconversationallicense:miteval-results

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

    Auto-discovered from HuggingFace trending. 1371 likes, 3.5M downloads.

  • DeepSeek V4 ProOpen

    deepseek-ai · self-host

    ▾

    Best for: Trending on HuggingFace (4867 likes this week)

    How: Available on Hugging Face. 2935K 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. 4867 likes, 2.9M 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.