The 20B variant of OpenAI's open source model. Apache 2.0 licensed.

State-of-the-art image + text input models from Google, built from the...

Distilled version of the DeepSeek-R1-0528 model, created by continuing...

Gemma 3n is a multimodal generative AI model optimized for use in ever...

The 8B parameter version of the Qwen3 model family.

A powerful 30B MoE coding model from Alibaba Qwen, joining its larger ...

State-of-the-art image + text input models from Google, built from the...

Updated thinking version of Qwen3 4B featuring continued scaling of th...

State-of-the-art image + text input models from Google, built from the...

Update to Mistral Small 3.1 with better instruction following, fewer i...

Updated version of Qwen3-30B-A3B featuring significant improvements in...

Lightweight open model from the Phi-4 family

One of the most popular open-source LLMs, Mistral's 7B Instruct model'...

Advanced open-weight reasoning model, finetuned from Phi-4 with additi...

The 14B parameter version of the Qwen3 model family.

The 120B variant of OpenAI's open source model. Apache 2.0 licensed.

Hybrid architecture model intended for local use, by Liquid AI

The 32B parameter version of the Qwen3 model family.

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

The 4B parameter version of the Qwen3 model family.