LLM Models · Open Source
Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.
This model always redirects to the latest model in the DeepSeek Pro family.
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc.
[!Note] This repository contains FP8-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc. The quantization method is fine-g…
Description: The NVIDIA Qwen3.8-27B NVFP4 model is a quantized version of Alibaba's Qwen3.8-27B model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information on the model, please check here. The model is quantized with Mod…
[!Note] This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, KTransformers, etc.
[ModelPage] : https://static.stepfun.com/blog/step-3.7-flash/
[ModelPage] : https://static.stepfun.com/blog/step-3.7-flash/
[ModelPage] : https://static.stepfun.com/blog/step-3.7-flash/
We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.
MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.