TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ

Quantization vs mistralai/Mixtral-8x7B-Instruct-v0.1. TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ is a quantized version of the other (I32/BF16).

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse