mobiuslabsgmbh
/

Mixtral-8x7B-Instruct-v0.1-hf-4bit_g64-HQQ

Text Generation

Mixture of Experts

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (1)

Serving with TGI or vLLM?

#3 opened 6 months ago by

only use one gpu?

#2 opened 7 months ago by

persist dequantized model

#1 opened 7 months ago by