mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ

Update README.md

Update README.md

Update README.md

update qmodel with gs=128

Update README.md

Update README.md

screencast

adding streaming in the example provided

adding vram usage

adding initial metrics

Update README.md

Update README.md

upload model

Update README.md

initial commit