Hugging Face Generative AI Services (HUGS) documentation

Supported Models

Hugging Face Generative AI Services (HUGS)

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Supported Models

HUGS supports a wide range of open AI models, including LLMs, Multimodal Models, and Embedding Models. Below is a matrix of all the models supported by HUGS and the hardware they are supported on.

13 Models Supported

Model	1x NVIDIA A10G	2x NVIDIA A10G	4x NVIDIA A10G	8x NVIDIA A10G	1x NVIDIA L4	2x NVIDIA L4	4x NVIDIA L4	8x NVIDIA L4	1x NVIDIA L40S	2x NVIDIA L40S	4x NVIDIA L40S	8x NVIDIA L40S	1x NVIDIA A100 80GB	2x NVIDIA A100 80GB	4x NVIDIA A100 80GB	8x NVIDIA A100 80GB	1x NVIDIA H100	2x NVIDIA H100	4x NVIDIA H100	8x NVIDIA H100	8x AMD Instinct MI300X
meta-llama/Llama-3.1-8B-Instruct	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
meta-llama/Llama-3.1-70B-Instruct	❌	❌	❌	✅	❌	❌	❌	✅	❌	❌	✅	✅	❌	❌	✅	✅	❌	❌	✅	✅	✅
meta-llama/Llama-3.1-405B-Instruct-FP8	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✅	❌
NousResearch/Hermes-3-Llama-3.1-8B	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
NousResearch/Hermes-3-Llama-3.1-70B	❌	❌	❌	✅	❌	❌	❌	✅	❌	❌	✅	✅	❌	❌	✅	✅	❌	❌	✅	✅	✅
NousResearch/Hermes-3-Llama-3.1-405B-FP8	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✅	❌
NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO	❌	❌	❌	✅	❌	❌	❌	✅	❌	❌	✅	✅	❌	✅	✅	✅	❌	✅	✅	✅	✅
mistralai/Mixtral-8x7B-Instruct-v0.1	❌	❌	❌	✅	❌	❌	❌	✅	❌	❌	✅	✅	❌	✅	✅	✅	❌	✅	✅	✅	✅
mistralai/Mistral-7B-Instruct-v0.3	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
mistralai/Mixtral-8x22B-Instruct-v0.1	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	❌	✅	❌	❌	❌	✅	❌	❌	❌	✅	✅
google/gemma-2-27b-it	❌	❌	✅	✅	❌	❌	✅	✅	❌	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
google/gemma-2-9b-it	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
Qwen/Qwen2.5-7B-Instruct	✅	✅	✅	❌	✅	✅	✅	❌	✅	✅	✅	❌	✅	✅	✅	❌	✅	✅	✅	❌	❌

Last Updated: 2024-10-18

< > Update on GitHub

←Hugging Face Generative AI Services (HUGS) Supported Hardware Providers→