Mixtral-8x7B-Instruct-v0.1-W4A8-AWQ

W4A8_AWQ quantization with ModelOpt for Mixtral-8x7B-Instruct-v0.1.

Downloads last month
1
Safetensors
Model size
24B params
Tensor type
F32
BF16
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support