AI Models

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.

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).

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.

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

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

Best for: Faster self-hosted inference, cost-efficient multimodal

How: MoE variant — faster inference than the 31B dense. Same multimodal capabilities.

Example: Process image-based monitoring alerts faster than the dense variant at the same quality.

API: Ollama, vLLM, Hugging Face. ollama run gemma4:27b-moe

Best for: Edge, mobile, IoT, on-device AI with multimodal input

How: 4B params — runs on any hardware. Supports images, video, AND native audio input.

Example: Run on a Raspberry Pi to process security camera feeds with voice commands.

API: Ollama, Hugging Face. Runs on phones and Raspberry Pi.

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.

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

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.

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

Best for: Edge deployment, on-device AI, lightweight vision tasks

How: 3B fits on phones, 8B on laptops, 14B on dev GPUs. All have vision support.

Example: Run 8B on a Jetson to classify manufacturing defects from camera feeds.

API: Ollama, vLLM, Hugging Face. Also on Mistral API.

Best for: Cost-sensitive Chinese-market video, fast iteration on social shorts, longer narrative clips.

How: Two tiers — Seedance 2.0 Pro for quality and Seedance 2.0 Lite for fast/cheap drafts. Both expose text-to-video and image-to-video; v2 adds longer shot length and stronger prompt adherence over v1.

Example: POST volcengineapi.com/seedance/v2/videos { prompt: 'a hummingbird in flight, slow motion', mode: 'pro' }

API: Volcengine / ByteDance API

Successor to Seedance 1.0 (2025-06). ByteDance's competitor to Sora / Veo / Kling. The Lite tier remains notably cheaper than competitors at comparable quality.

Best for: Marketing reels, b-roll, storyboard previz, social-media shorts.

How: Generate up to 60s clips from a text prompt or seed image. Audio and lip-sync included.

Example: client.videos.generate(model='sora-2', prompt='aerial shot of a coastal city at sunrise, 1080p, 10s')

API: api.openai.com — client.videos.generate(model='sora-2')

Successor to Sora 1 — adds native audio and longer coherent shots.

Best for: Best-in-class open-source video. The 5B variant runs on a single 24GB consumer card.

How: ComfyUI nodes ship official support. Or `python generate.py --task t2v-A14B --prompt '...'` from the WanX repo.

Example: python generate.py --task t2v-A14B --prompt 'a corgi running on the beach at sunset' --resolution 720P

API: huggingface.co/Wan-AI/Wan2.2-T2V-A14B · Wan-AI/Wan2.2-T2V-5B

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.

API: api.moonshot.ai — OpenAI-compatible

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.

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

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.

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

Best for: High-volume processing, real-time apps, budget-conscious pipelines

How: Set thinking_budget to control reasoning cost. 0 = no thinking, 24576 = max.

Example: Summarize 1000 GitHub issues per hour for a triage dashboard at ~$1.

API: Same SDK as Gemini Pro. model='gemini-2.5-flash-preview-05-20'

Best for: Photoreal cinematic clips, ad creative, talking-head shorts with audio.

How: Vertex AI: generate(model='veo-3.0-generate-preview', prompt='...'). Gemini API exposes the same model.

Example: ai.models.generate_videos(model='veo-3.0-generate-preview', prompt='timelapse of a city under heavy rain')

API: Vertex AI / Gemini API — model: veo-3.0-generate-preview

Best for: Pipelines, batch processing, structured data extraction, routing

How: Use for high-volume, low-complexity tasks: classification, extraction, summarization.

Example: Process 10K support tickets per hour to classify priority and extract entities.

API: api.anthropic.com — same SDK

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.

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

Best for: Embeddings preprocessing, log parsing, lightweight generation

How: Same API as GPT-4.1. Best for high-volume, simple tasks where cost matters.

Example: Parse 50K structured logs per hour and extract error patterns.

API: api.openai.com — same SDK

Best for: Intent classification, entity extraction at massive scale

How: Use for routing, tagging, simple extraction where quality bar is lower.

Example: Route 1M incoming messages per day to the right service for $4 total.

API: api.openai.com — same SDK

Best for: Hard math, science, multi-step planning, complex debugging

How: Use reasoning_effort param: 'low'/'medium'/'high'. No system prompt — use developer message instead.

Example: Debug a distributed system deadlock by feeding it the full trace + architecture.

API: api.openai.com — same SDK, just model='o3'

Best for: Coding with reasoning, moderate-complexity math, budget reasoning

How: Cheaper reasoning model. Use when o3 is overkill but you need chain-of-thought.

Example: Generate a migration plan for a database schema change with safety checks.

API: api.openai.com — same SDK

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.

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

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.

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

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.

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

Best for: Local development, laptop-friendly reasoning, privacy

How: Excellent for local dev. MoE means only 3B params active — fast on consumer hardware.

Example: Run on your dev machine as a private coding assistant with reasoning.

API: ollama run qwen3:30b — fits on RTX 4090 (24GB)

Best for: UI mockups, marketing assets, diagrams with text

How: Supports text overlays, inpainting, and style control. Best text rendering of any model.

Example: Generate architecture diagrams with accurate labels from a text description.

API: api.openai.com — client.images.generate(model='gpt-image-1')

Best for: Cost-sensitive video generation, dance / sports content.

How: Cheaper alternative to Sora/Veo with strong human-motion fidelity.

Example: POST klingai.com/v1/videos/text2video { prompt: '...', duration: 10 }

API: klingai.com — REST API

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.

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

Best for: On-device/edge deployment, multimodal at small scale

How: ollama run gemma3:27b. Fits on RTX 3090/4090. Good multimodal + tool use at small size.

Example: Run on a dev server to process screenshots and generate bug reports.

API: Ollama, vLLM, Hugging Face. Also on Vertex AI.

Best for: Short narrative content where the same character appears in multiple scenes.

How: Pass a reference image and a prompt; returns a 5–10s clip with consistent characters across shots.

Example: POST runwayml.com/v1/image_to_video { promptImage: ..., promptText: '...' }

API: runwayml.com — REST API + web app

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.

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

Best for: Budget reasoning tasks, math, lightweight chain-of-thought

How: Excellent cost-to-reasoning ratio. Use reasoning_effort param.

Example: Validate Terraform plans with reasoning about dependency chains for pennies.

API: api.x.ai — same as Grok 3

Best for: Self-hosted RAG, privacy-first search, zero-cost embeddings

How: Self-host for zero cost. Comparable quality to OpenAI embeddings.

Example: Run alongside pgvector on the same server — full RAG pipeline with zero API costs.

API: pip install nomic OR Ollama. Also hosted on Nomic Atlas.

Best for: Highest-quality open-source video model when you have the hardware to run it.

How: Clone stepfun-ai/Step-Video-T2V repo, install requirements, run sample.py with your prompt.

Example: python sample_video.py --prompt 'underwater coral reef, schools of fish' --num-frames 204 --resolution 544x992

API: huggingface.co/stepfun-ai/stepvideo-t2v

Best for: Budget reasoning, self-hosted chain-of-thought, research

How: API is OpenAI-compatible. Self-host the 70B distill on 2x A100. MIT license = no restrictions.

Example: Run the 14B distill locally for debugging complex distributed system issues.

API: api.deepseek.com ($0.55/M in, $2.19/M out) OR self-host via vLLM/Ollama

Best for: Code completion, inline suggestions, editor integration

How: Supports FIM for inline completion. Integrate with any editor via LSP or Continue.dev.

Example: Deploy as your team's FIM-capable completion server behind an LSP proxy.

API: codestral.mistral.ai — dedicated code endpoint

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.

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

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.

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

Best for: Edge deployment, STEM tasks, embedded AI in products

How: ollama run phi4. MIT license — embed in commercial products freely.

Example: Embed in a CI pipeline to validate config files and Terraform plans.

API: Ollama, Hugging Face, Azure AI

Best for: Social shorts, music videos, rapid creative iteration.

How: Strong for short, stylized clips and quick iteration. Pikaframes lets you set start/end frames.

Example: Use Pikaframes: upload start + end image, prompt the in-between motion.

API: pika.art — web app + API

Best for: Self-hosted video generation, research, building custom pipelines.

How: Clone repo, install diffusers, run sample.py with your prompt. Or use ComfyUI workflows.

Example: python sample_video.py --prompt 'a cat surfing at sunset' --video-length 129 --infer-steps 50

API: huggingface.co/tencent/HunyuanVideo

Best for: Private code completion, self-hosted Copilot replacement

How: ollama run qwen2.5-coder:32b. Plug into Continue.dev or Copilot alternatives.

Example: Set up as your team's private code completion backend — zero data leaves your infra.

API: Ollama, vLLM, or hosted on Together/Fireworks

Best for: When you need quick turnaround — prototypes, drafts, dataset generation. Speed-first open-source video.

How: diffusers LTXPipeline. Generates a 5-second 768×512 clip in seconds on an H100; a few minutes on a 4090.

Example: from diffusers import LTXPipeline; pipe = LTXPipeline.from_pretrained('Lightricks/LTX-Video'); pipe(prompt='falling autumn leaves').frames

API: huggingface.co/Lightricks/LTX-Video · Lightricks/LTX-Video-13B

Best for: Open-source video where commercial use matters — the Apache 2.0 license is unrestricted.

How: Diffusers pipeline or the official genmoai/models repo. ComfyUI workflows are well-documented.

Example: python -m mochi_preview.cli --prompt 'time lapse of a city street at golden hour' --num-frames 84

API: huggingface.co/genmo/mochi-1-preview

Best for: High-quality image generation, product photography

How: API or self-host Flux.1 Schnell (open). Pro via API only.

Example: Generate product mockups for landing pages programmatically.

API: api.bfl.ml OR via Replicate, fal.ai

Best for: Pioneer open-source T2V — solid baseline for self-hosted experimentation and fine-tuning.

How: pip install diffusers; CogVideoXPipeline.from_pretrained('THUDM/CogVideoX-5b') and run with a text prompt.

Example: from diffusers import CogVideoXPipeline; pipe = CogVideoXPipeline.from_pretrained('THUDM/CogVideoX-5b'); pipe(prompt='a panda playing piano').frames

API: huggingface.co/THUDM/CogVideoX-5b

Best for: Batch processing, structured extraction, JSON pipelines

How: Best for structured output tasks. Supports response_format: json_object. No reasoning overhead.

Example: Process RSS feeds into structured summaries for pennies per 1000 articles.

API: api.moonshot.ai — OpenAI-compatible. model='moonshot-v1-8k'

Best for: RAG pipelines, semantic search, document retrieval

How: Set dimensions param to reduce size (e.g., 256 for fast search, 3072 for max quality).

Example: Index your internal docs and build a search API with pgvector + this model.

API: api.openai.com — client.embeddings.create(model='text-embedding-3-large')

Best for: computational biology tasks

How: Fine-tune ESM2 using NVIDIA BioNeMo recipes

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

Auto-discovered from news articles.

Best for: Computational biology tasks

How: Use NVIDIA BioNeMo recipes for fine-tuning

Example: Fine-tuning ESM2 protein language models

Auto-discovered from news articles.

Best for: petite PC development

How: work with either Microsoft Windows or Linux

Example: use in AI development platforms

Auto-discovered from news articles.

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)

Auto-discovered from news articles.

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

Auto-discovered from news articles.

Best for: Training speech AI models for clinical applications

How: Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech

Example: Training a speech AI model to correctly recognize drug names like Acetaminophen, Amlodipine

Auto-discovered from news articles.

Best for: maintaining context and completing tasks across many turns

How: deploy on Renesas RZ/V series for production

Example: use in chatbots evolving into long-running agents

Auto-discovered from news articles.

Best for: Maintaining context and efficiency across many turns

How: Integrate with existing chatbot frameworks to enhance long-running agent capabilities

Example: Use Nemotron 3 Ultra to power a chatbot that can reason and maintain context over multiple interactions

Auto-discovered from news articles.

Best for: Mobile and laptop applications requiring efficient AI models

How: Integrate Gemma 4 QAT models into your application for on-device AI processing

Example: Use Gemma 4 QAT for image recognition on smartphones with low latency and power consumption

Auto-discovered from news articles.

Best for: expanding on-device AI capabilities in Microsoft Edge

How: use Prompt and Writing Assistance APIs in Microsoft Edge

Example: integrated with Microsoft Edge for on-device AI tasks

Auto-discovered from news articles.

Best for: Advanced AI tasks

How: Integrate Mellum2 into your AI workflows

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

Auto-discovered from news articles.

Best for: Developing Physical AI systems that need to understand and act within the real world

How: Integrate NVIDIA Cosmos 3 into your Physical AI system to enable reasoning and action capabilities

Example: Using NVIDIA Cosmos 3 to develop a robot that can understand and interact with its environment

Auto-discovered from news articles.

Best for: General AI applications

How: Integrate with Google I/O 2026

Example: Watch 9 videos showing the capabilities of Gemini 3.5

Auto-discovered from news articles.

Best for: General AI applications

How: Integrate with Google I/O 2026

Example: Watch 9 videos showing the capabilities of Gemini Omni

Auto-discovered from news articles.

Best for: Trending on HuggingFace (2063 likes this week)

How: Available on Hugging Face. 87K downloads.

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

API: huggingface.co/nvidia/LocateAnything-3B

Auto-discovered from HuggingFace trending. 2063 likes, 87K downloads.

Best for: financial trading landscape

How: Enables sophisticated analysis

Example: revolutionizing financial trading landscape

Auto-discovered from news articles.

Best for: conversational AI and content generation in Portuguese

How: Use ChatGPT API to integrate with applications

Example: Generate news articles in Portuguese

Auto-discovered from news articles.

Best for: governments, enterprises, and telcos

How: N/A

Example: N/A

Auto-discovered from news articles.

Best for: container workflow management

How: Integrate Gordon with Docker Desktop

Example: Gordon proposes fixes and takes action across your entire Docker workflow

Auto-discovered from news articles.

Best for: analyzing live code across critical parts of infrastructure

How: Point Mythos at live code to observe its strengths and weaknesses

Example: Mythos was used to analyze live code across critical parts of Cloudflare's infrastructure

Auto-discovered from news articles.

Best for: Trending on HuggingFace (101 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("ScenemaAI/scenema-audio")

API: huggingface.co/ScenemaAI/scenema-audio

Auto-discovered from HuggingFace trending. 101 likes, 237 downloads.

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")

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

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

Best for: Trending on HuggingFace (239 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("ResembleAI/Dramabox")

API: huggingface.co/ResembleAI/Dramabox

Auto-discovered from HuggingFace trending. 239 likes, 1K downloads.

Best for: Trending on HuggingFace (1084 likes this week)

How: Available on Hugging Face. 445K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM-V-4.6")

API: huggingface.co/openbmb/MiniCPM-V-4.6

Auto-discovered from HuggingFace trending. 1084 likes, 445K downloads.

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")

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

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

Best for: Trending on HuggingFace (418 likes this week)

How: Available on Hugging Face. 16K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("SeeSee21/Z-Anime")

API: huggingface.co/SeeSee21/Z-Anime

Auto-discovered from HuggingFace trending. 418 likes, 16K downloads.

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")

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

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

Best for: Trending on HuggingFace (564 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("RuneXX/LTX-2.3-Workflows")

API: huggingface.co/RuneXX/LTX-2.3-Workflows

Auto-discovered from HuggingFace trending. 564 likes, 0 downloads.

Best for: Trending on HuggingFace (593 likes this week)

How: Available on Hugging Face. 15K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("microsoft/Fara-7B")

API: huggingface.co/microsoft/Fara-7B

Auto-discovered from HuggingFace trending. 593 likes, 15K downloads.

Best for: Agentic inference workloads

How: Integrate with NVIDIA's platform for inference

Example: Use for non-deterministic trajectories in AI

Auto-discovered from news articles.

Best for: function-calling tasks

How: run Needle on consumer devices

Example: function-calling (tool use) model

Auto-discovered from news articles.

Best for: Trending on HuggingFace (105 likes this week)

How: Available on Hugging Face. 144K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF")

API: huggingface.co/DavidAU/Qwen3.6-27B-Heretic-Uncensored-FINETUNE-NEO-CODE-Di-IMatrix-MAX-GGUF

Auto-discovered from HuggingFace trending. 105 likes, 144K downloads.

Best for: Trending on HuggingFace (281 likes this week)

How: Available on Hugging Face. 136K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("TenStrip/LTX2.3-10Eros")

API: huggingface.co/TenStrip/LTX2.3-10Eros

Auto-discovered from HuggingFace trending. 281 likes, 136K downloads.

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")

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

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

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")

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

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

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")

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

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

Best for: Trending on HuggingFace (872 likes this week)

How: Available on Hugging Face. 2236K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("k2-fsa/OmniVoice")

API: huggingface.co/k2-fsa/OmniVoice

Auto-discovered from HuggingFace trending. 872 likes, 2.2M downloads.

Best for: defensive cyber tasks

How: use the model for specialized cyber defense tasks

Example: model can be used for detecting and preventing cyber threats

Auto-discovered from news articles.

Best for: local AI applications on Windows and Linux

How: integrate with Lemonade SDK

Example: use GAIA for local AI tasks on Windows and Linux systems

Auto-discovered from news articles.

Best for: AI-powered game development

How: Integrate NVIDIA DLSS 4.5 with Unreal Engine 5

Example: Game developers can enhance game performance and visuals

Auto-discovered from news articles.

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")

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

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

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")

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

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

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")

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

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

Best for: Trending on HuggingFace (265 likes this week)

How: Available on Hugging Face. 303K downloads.

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

API: huggingface.co/HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive

Auto-discovered from HuggingFace trending. 265 likes, 303K downloads.

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")

API: huggingface.co/tencent/Hy3-preview

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

Best for: Cost-sensitive Chinese-market video, fast iteration on social shorts.

How: Two tiers: Seedance 1.0 Pro for top quality and Seedance 1.0 Lite for fast/cheap drafts. Both expose text-to-video and image-to-video.

Example: POST volcengineapi.com/seedance/v1/videos { prompt: 'a hummingbird in flight, slow motion', mode: 'pro' }

API: Volcengine / ByteDance API

ByteDance's competitor to Sora / Veo / Kling. Lite tier is notably cheaper than competitors at similar quality.

Best for: multimodal agent reasoning in a single efficient open model

How: Run NVIDIA Nemotron 3 Nano Omni locally in a single command

Example: reasoning across screens, documents, audio, video, and text within a single perception-to-action loop

Auto-discovered from news articles.

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")

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

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

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

Auto-discovered from news articles.

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

Auto-discovered from news articles.

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

How: Available on Hugging Face. 745K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B-FP8")

API: huggingface.co/Qwen/Qwen3.6-27B-FP8

Auto-discovered from HuggingFace trending. 160 likes, 745K downloads.

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

Auto-discovered from news articles.

Best for: AI acceleration

How: deploy Google TPUv8 in your cloud environment

Example: use Google TPUv8 for AI model training and inference

Auto-discovered from news articles.

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.

Auto-discovered from news articles.

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.

Auto-discovered from news articles.

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")

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

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

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")

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

Auto-discovered from HuggingFace trending. 4867 likes, 2.9M downloads.

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

Auto-discovered from news articles.

Best for: text privacy and compliance

How: Integrate into text processing workflows

Example: Automatically redact sensitive information from documents

Auto-discovered from news articles.

Best for: AI acceleration

How: Deploy in Google Cloud for AI tasks

Example: Use for training and inference in AI applications

Auto-discovered from news articles.

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")

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

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

Best for: Trending on HuggingFace (633 likes this week)

How: Available on Hugging Face. 1355K downloads.

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

API: huggingface.co/unsloth/Qwen3.6-27B-GGUF

Auto-discovered from HuggingFace trending. 633 likes, 1.4M downloads.

Best for: Trending on HuggingFace (1554 likes this week)

How: Available on Hugging Face. 5064K downloads.

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

API: huggingface.co/Qwen/Qwen3.6-27B

Auto-discovered from HuggingFace trending. 1554 likes, 5.1M downloads.

Best for: enterprises to deploy and scale Codex

How: partner with Accenture, PwC, Infosys, and others

Example: help enterprises deploy and scale Codex across the software development lifecycle

Auto-discovered from news articles.

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")

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

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

Best for: Trending on HuggingFace (1197 likes this week)

How: Available on Hugging Face. 825K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("moonshotai/Kimi-K2.6")

API: huggingface.co/moonshotai/Kimi-K2.6

Auto-discovered from HuggingFace trending. 1197 likes, 825K downloads.

Best for: Trending on HuggingFace (158 likes this week)

How: Available on Hugging Face. 490K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-35B-A3B-FP8")

API: huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8

Auto-discovered from HuggingFace trending. 158 likes, 490K downloads.

Best for: Trending on HuggingFace (1860 likes this week)

How: Available on Hugging Face. 2698K downloads.

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

API: huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

Auto-discovered from HuggingFace trending. 1860 likes, 2.7M downloads.

Best for: life sciences research

How: N/A

Example: N/A

Auto-discovered from news articles.

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

How: Available on Hugging Face. 30K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("unsloth/ERNIE-Image-Turbo-GGUF")

API: huggingface.co/unsloth/ERNIE-Image-Turbo-GGUF

Auto-discovered from HuggingFace trending. 180 likes, 30K downloads.

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")

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

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

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")

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

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

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")

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

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

Best for: Trending on HuggingFace (1487 likes this week)

How: Available on Hugging Face. 170K downloads.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("dealignai/Gemma-4-31B-JANG_4M-CRACK")

API: huggingface.co/dealignai/Gemma-4-31B-JANG_4M-CRACK

Auto-discovered from HuggingFace trending. 1487 likes, 170K downloads.

Best for: Trending on HuggingFace (344 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("baidu/ERNIE-Image-Turbo")

API: huggingface.co/baidu/ERNIE-Image-Turbo

Auto-discovered from HuggingFace trending. 344 likes, 6K downloads.

Best for: Trending on HuggingFace (966 likes this week)

How: Available on Hugging Face. 2500K downloads.

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

API: huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF

Auto-discovered from HuggingFace trending. 966 likes, 2.5M downloads.

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")

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

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

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")

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

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

Best for: Trending on HuggingFace (550 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("baidu/ERNIE-Image")

API: huggingface.co/baidu/ERNIE-Image

Auto-discovered from HuggingFace trending. 550 likes, 7K downloads.

Best for: Trending on HuggingFace (897 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("tencent/HY-Embodied-0.5")

API: huggingface.co/tencent/HY-Embodied-0.5

Auto-discovered from HuggingFace trending. 897 likes, 2K downloads.

Best for: Trending on HuggingFace (1803 likes this week)

How: Available on Hugging Face. 5477K downloads.

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

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

Auto-discovered from HuggingFace trending. 1803 likes, 5.5M downloads.

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")

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

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

Best for: Trending on HuggingFace (213 likes this week)

How: Available on Hugging Face.

Example: from transformers import AutoModelForCausalLM; model = AutoModelForCausalLM.from_pretrained("NucleusAI/Nucleus-Image")

API: huggingface.co/NucleusAI/Nucleus-Image

Auto-discovered from HuggingFace trending. 213 likes, 2K downloads.

Best for: Trending on HuggingFace (2640 likes this week)

How: Available on Hugging Face. 9794K downloads.

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

API: huggingface.co/google/gemma-4-31B-it

Auto-discovered from HuggingFace trending. 2640 likes, 9.8M downloads.