Edit model card

This is a working version of Mixtral Instruct that is AWQ quantized. As of 11-02-2024, https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ is not working, so please use this repository instead.

Downloads last month
14,524
Safetensors
Model size
6.48B params
Tensor type
I32
·
FP16
·
Inference API
Input a message to start chatting with casperhansen/mixtral-instruct-awq.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.

Space using casperhansen/mixtral-instruct-awq 1