Hugging Quants

12 indexed models

12 matching models

hugging-quants-gemma-2-9b-it-awq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-gemma-2-9b-it-awq-int4@1

`hugging-quants/gemma-2-9b-it-AWQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/gemma-2-9b-it-AWQ-INT4) - [Text Generation

Input modalities
text
Output modalities
text

hugging-quants-meta-llama-3.1-405b-instruct-awq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-405b-instruct-awq-int4@1

`hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-405B-Instruc

Input modalities
text
Output modalities
text

hugging-quants-meta-llama-3.1-70b-instruct-awq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-70b-instruct-awq-int4@1

`hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-70B-Instruct-

Input modalities
text
Output modalities
text

hugging-quants-meta-llama-3.1-70b-instruct-gptq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-70b-instruct-gptq-int4@1

`hugging-quants/Meta-Llama-3.1-70B-Instruct-GPTQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-70B-Instruct

Input modalities
text
Output modalities
text

hugging-quants/Meta-Llama-3.1-8B-BNB-NF4

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-8b-bnb-nf4@1

`hugging-quants/Meta-Llama-3.1-8B-BNB-NF4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-BNB-NF4) - [Text Gene

Input modalities
text
Output modalities
text

hugging-quants-meta-llama-3.1-8b-instruct-awq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-8b-instruct-awq-int4@1

`hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-AW

Input modalities
text
Output modalities
text

hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-8b-instruct-bnb-nf4@1

`hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB-NF4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-BNB

Input modalities
text
Output modalities
text

hugging-quants-meta-llama-3.1-8b-instruct-gptq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-meta-llama-3.1-8b-instruct-gptq-int4@1

`hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Meta-Llama-3.1-8B-Instruct-G

Input modalities
text
Output modalities
text

hugging-quants-mixtral-8x7b-instruct-v0.1-awq-int4 · HuggingFace v1

azureFoundry/HuggingFace/hugging-quants-mixtral-8x7b-instruct-v0.1-awq-int4@1

`hugging-quants/Mixtral-8x7B-Instruct-v0.1-AWQ-INT4` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/hugging-quants/Mixtral-8x7B-Instruct-v0.1-AW

Input modalities
text
Output modalities
text

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace