Model Catalog

Distilled version of the DeepSeek-R1-0528 model, created by continuing the post-training process on the Qwen3 8B Base model using Chain-of-Thought (CoT) from DeepSeek-R1-0528.

Devstral by MistralAI is based on Mistral Small 3.1. Debuts as the #1 open source model on SWE-bench.

Lightweight open model from the Phi-4 family

Advanced open-weight reasoning model, finetuned from Phi-4 with additional reinforcement learning for higher accuracy

The 235B parameter (MoE) version of the Qwen3 model family.

The 32B parameter version of the Qwen3 model family.

The 30B parameter (MoE) version of the Qwen3 model family.

The 1.7B parameter version of the Qwen3 model family.

The 4B parameter version of the Qwen3 model family.

The 14B parameter version of the Qwen3 model family.

The 8B parameter version of the Qwen3 model family.

State-of-the-art image + text input models from Google, built from the same research and tech used to create the Gemini models

State-of-the-art image + text input models from Google, built from the same research and tech used to create the Gemini models

State-of-the-art image + text input models from Google, built from the same research and tech used to create the Gemini models

Tiny text-only variant of Gemma 3: Google's latest open-weight model family

Reasoning model from the Qwen family, rivaling DeepSeek R1 on benchmarks.

A small and capable LLM from IBM

a 7B Vision Language Model (VLM) from the Qwen2.5 family

The latest in the Phi model series: suitable for chats with a context of up to 16K tokens

Dense LLM from IBM supporting up to 128K context length, trained on 12T tokens. Suitable for general instructions following and can be used to build AI assistants

Meta's latest Llama 70B model, matches the performance of Llama 3.2 405B

14B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

32B version of the code-specific Qwen 2.5 for code generation, code reasoning and code fixing.

A slightly larger 12B parameter model from Mistral AI, NeMo offers a long 128k token context length, advanced world knowledge, and function calling for developers.

A scientific specialist finetune of Mistral AI's popular 7B model, Mathstral excels at STEM chats and tasks.

The mid-sized option of the Gemma 2 model family. Built by Google, using from the same research and technology used to create the Gemini models

The large option of the Gemma 2 model family. Built by Google, using from the same research and technology used to create the Gemini models

Mistral AI's latest coding model, Codestral can handle both instructions and code completions with ease in over 80 programming languages.

One of the most popular open-source LLMs, Mistral's 7B Instruct model's balance of speed, size, and performance makes it a great general-purpose daily driver.