nisten
/

qwenv2-7b-inst-imatrix-gguf

Inference Endpoints

Model card Files Files and versions Community

qwenv2-7b-inst-imatrix-gguf / qwen7bv2_iq4xs_output8bit.gguf

Commit History

Probably best speed to perplexity ratio of any 7b gguf model so far

0e76852
verified

nisten commited on Jun 16