Model Families

8 model families with variants across different sizes.

Command R

Cohere

Cohere's Command R is a family of models optimized for retrieval-augmented generation (RAG) and enterprise use cases. Co...

1 variant 35B — 35B

DeepSeek R1

DeepSeek

DeepSeek's R1 family of reasoning-focused open-weight models, trained with reinforcement learning to excel at complex mu...

4 variants 7B — 70B

Gemma 2

Google

Google's Gemma 2 is a family of lightweight, open-weight models built from the same research and technology used to crea...

3 variants 2B — 27B

Llama 3

Meta

Meta's Llama 3 is one of the most capable and widely adopted open-weight model families. Spanning from compact 1B parame...

6 variants 1B — 405B

Mistral

Mistral AI

Mistral AI's open-weight model family, known for exceptional efficiency and strong performance relative to model size. I...

3 variants 7B — 47B

Phi

Microsoft

Microsoft's Phi family of small language models, designed to demonstrate that carefully curated training data can enable...

2 variants 3.8B — 14B

Qwen 2.5

Alibaba

Alibaba's Qwen 2.5 is a comprehensive family of open-weight models spanning from 7B to 72B parameters, with specialized ...

5 variants 7B — 72B

StarCoder

BigCode

BigCode's StarCoder is a family of code-specialized language models developed as part of an open scientific collaboratio...

1 variant 15B — 15B