AI Models

Open-weight models you can run on your own hardware

Code Llama 34B

34B

Meta

Meta's specialized coding model built on Llama 2. Excels at code generation, completion, and debugging across multiple p...

codingcode-completiondebugging
🖥️ 24 GB 📏 16K 📄 Llama 2 Community

Command R

35B

Cohere

Cohere's RAG-optimized model designed for enterprise search and retrieval tasks. Excels at grounded generation with cita...

RAGsearchtool-use
🖥️ 24 GB 📏 128K 📄 CC-BY-NC-4.0

DeepSeek R1 14B

14B

DeepSeek

Mid-size reasoning model with excellent chain-of-thought capabilities. Balances performance and resource requirements we...

reasoningmathcoding
🖥️ 16 GB 📏 128K 📄 MIT

DeepSeek R1 32B

32B

DeepSeek

High-performance reasoning model that rivals much larger models. Excellent for complex problem solving, mathematics, and...

reasoningmathcoding
🖥️ 24 GB 📏 128K 📄 MIT

DeepSeek R1 70B

70B

DeepSeek

The full DeepSeek R1 distilled to 70B parameters. State-of-the-art reasoning that competes with GPT-4 and Claude on math...

reasoningmathcoding
🖥️ 48 GB 📏 128K 📄 MIT

DeepSeek R1 7B

7B

DeepSeek

Compact reasoning model distilled from DeepSeek-R1, offering strong chain-of-thought reasoning in a small package. Great...

reasoningmathcoding
🖥️ 8 GB 📏 128K 📄 MIT

Gemma 2 27B

27B

Google

Google's largest Gemma model delivering near-Llama-70B quality at half the size. Excellent efficiency-to-performance rat...

chatreasoningcoding
🖥️ 24 GB 📏 8K 📄 Gemma

Gemma 2 2B

2B

Google

Google's ultra-lightweight model that runs anywhere. Ideal for on-device AI, edge computing, and rapid prototyping with ...

chatedgeprototyping
🖥️ 4 GB 📏 8K 📄 Gemma

Gemma 2 9B

9B

Google

Google's mid-range model offering strong performance across tasks. Uses knowledge distillation techniques for quality th...

chatreasoninggeneral
🖥️ 12 GB 📏 8K 📄 Gemma

Llama 3.2 1B

1B

Meta

Ultra-lightweight model perfect for edge devices, mobile phones, and IoT. Surprisingly capable for its tiny size, great ...

chatclassificationedge
🖥️ 4 GB 📏 128K 📄 Llama 3.2 Community

Llama 3.2 3B

3B

Meta

Small but mighty model that punches above its weight. Runs on almost any hardware and handles conversational AI, summari...

chatsummarizationedge
🖥️ 4 GB 📏 128K 📄 Llama 3.2 Community

Llama 3.3 70B

70B

Meta

Meta's latest instruction-tuned model with exceptional multilingual support and tool use. One of the best open-weight mo...

chatreasoningcoding
🖥️ 48 GB 📏 128K 📄 Llama 3.3 Community

Mistral 7B

7B

Mistral AI

The model that proved small models can compete. Mistral 7B uses sliding window attention and grouped-query attention for...

chatcodinginstruction-following
🖥️ 8 GB 📏 32K 📄 Apache 2.0

Mixtral 8x7B

46.7B (8x7B MoE)

Mistral AI

Mixture-of-experts model that activates only 12.9B parameters per token, giving near-70B quality at far lower compute co...

chatcodingmultilingual
🖥️ 32 GB 📏 32K 📄 Apache 2.0

Phi-4

14B

Microsoft

Microsoft's small language model that achieves remarkable performance through synthetic data training. Excels at reasoni...

reasoningmathcoding
🖥️ 16 GB 📏 16K 📄 MIT

Qwen 2.5 14B

14B

Alibaba

Mid-range powerhouse from Alibaba with exceptional coding benchmarks. Great balance of capability and resource requireme...

codingmathreasoning
🖥️ 16 GB 📏 128K 📄 Apache 2.0

Qwen 2.5 72B

72B

Alibaba

Alibaba's flagship open model rivaling GPT-4 class performance. Exceptional at coding, math, and multilingual tasks with...

codingmathreasoning
🖥️ 48 GB 📏 128K 📄 Apache 2.0

Qwen 2.5 7B

7B

Alibaba

Alibaba's latest 7B model with strong coding and math capabilities. Supports 29+ languages and excels at structured outp...

codingmathmultilingual
🖥️ 8 GB 📏 128K 📄 Apache 2.0