Self-Hosted AI with Hugging Face TGI

A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

MedGemma 1.5 4B is an updated version of the MedGemma 4B model.

FunctionGemma is a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

The template and tool-set of search agent have been updated, which is shown in assets/searchtooltrajectory.html.

DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.

The current, most capable model that runs on a single GPU.

Description: OpenReasoning-Nemotron-14B is a large language model (LLM) which is a derivative of Qwen2.5-14B (AKA the reference model). It is a reasoning model that is post-trained for reasoning about math, code and science solution generation. We evaluated this model with up to 64K output tokens.

MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.

Llama-3.1-Nemotron-Nano-4B-v1.1 is a large language model (LLM) which is a derivative of nvidia/Llama-3.1-Minitron-4B-Width-Base, which is created from Llama 3.1 8B using our LLM compression technique and offers improvements in model accuracy and efficiency.

Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.

NVIDIA Cosmos Reason – an open, customizable, 7B-parameter reasoning vision language model (VLM) for physical AI and robotics - enables robots and vision AI agents to reason like humans, using prior knowledge, physics understanding and common sense to understand and act in the real world.

Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.

Meta's latest collection of multimodal models.

Meta's latest collection of multimodal models.

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.

Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.1-8B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.

QwQ is the reasoning model of the Qwen series.

We introduce Nemotron-UltraLong-8B, a series of ultra-long context language models designed to process extensive sequences of text (up to 1M, 2M, and 4M tokens) while maintaining competitive performance on standard benchmarks.

SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

DeepSeek-R1 reasoning distilled into Qwen2.5 models, in 1.5B, 7B, 14B, and 32B sizes.

DeepSeek-R1 reasoning distilled into Llama 3.1 8B and Llama 3.3 70B.

A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.

Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.

An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

For more details, please refer to our blog. You can also check Qwen2.5 GitHub, and Documentation.