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

Gemma4, effective 4B version. Supports image input, reasoning, and too...

Qwen3.5 represents a significant leap forward, integrating breakthroug...

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

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

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

Gemma 4 is the latest on-device model family from Google. This is the ...

Dense 27B Qwen 3.6 prioritizes stability and real-world utility, offer...

Qwen3.6 prioritizes stability and real-world utility, offering develop...

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

Gemma 4 12B optimized with Quantized Aware Training

31B dense Gemma4 variant. Supports vision input, reasoning, and tool c...

Qwen3.5 is a reasoning vision-language model that supports tool use. W...

The 8B version of Qwen's latest vision-language model. Includes compre...

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

Gemma4, effective 2B version. Supports image input, reasoning, and too...

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

The 8B parameter version of the Qwen3 model family.

GLM 4.7 Flash is a 30B A3B MoE model form Z.ai. It supports a context ...

The reasoning post-trained version of Ministral 3 14B, optimized for c...