jarrelscy
/

Mixtral-8x22B-Instruct-v0.1-GPTQ-8bit

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.

Safetensors

Model size

36.9B params

Tensor type

I32

FP16

Inference Examples

Inference API (serverless) is not available, repository is disabled.