Edit model card

Model Card for Model ID

Optimum GPTQ quantized 8-bit version of Mixtral-8x22B-Instruct-v0.1
WIP - do not use currently
See original model card for more information.

How to load

Downloads last month
8
Safetensors
Model size
36.9B params
Tensor type
I32
·
FP16
·
Inference API
Input a message to start chatting with jarrelscy/Mixtral-8x22B-Instruct-v0.1-GPTQ-8bit.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.