nisten
/

qwenv2-7b-inst-imatrix-gguf

Inference Endpoints

Model card Files Files and versions Community

qwenv2-7b-inst-imatrix-gguf / qwen7bv2inst_iq4xs_output8bit.gguf

Commit History

best speed/perplexity quant for mobile devices with 8bit acceleration

d2b704a
verified

nisten commited on Jun 16