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.
15 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 | 2x inf2 | 8x inf2 | 24x inf2 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
meta-llama/Meta-Llama-3.1-8B-Instruct | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
meta-llama/Meta-Llama-3.1-70B-Instruct | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
meta-llama/Meta-Llama-3.1-405B-Instruct-FP8 | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
NousResearch/Hermes-3-Llama-3.1-8B | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
NousResearch/Hermes-3-Llama-3.1-70B | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
NousResearch/Hermes-3-Llama-3.1-405B-FP8 | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
mistralai/Mixtral-8x7B-Instruct-v0.1 | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
mistralai/Mistral-7B-Instruct-v0.3 | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
mistralai/Mixtral-8x22B-Instruct-v0.1 | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
google/gemma-2-27b-it | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
google/gemma-2-9b-it | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
Qwen/Qwen2.5-7B-Instruct | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
meta-llama/Llama-3.2-11B-Vision-Instruct | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
meta-llama/Llama-3.2-90B-Vision-Instruct | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β | β |
Last Updated: 2024-11-28
< > Update on GitHub