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
4,062
Safetensors
Model size
6.48B params
Tensor type
I32
·
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Space using casperhansen/mixtral-instruct-awq 1