nisten
/

qwenv2-7b-inst-imatrix-gguf

Inference Endpoints

Model card Files Files and versions Community

qwenv2-7b-inst-imatrix-gguf / qwen7bv2instruct_q8.gguf

Commit History

Best q8 conversion down from bf16 with slightly better perplexity than f16 based quants

bc0fa51
verified

nisten commited on Jun 16