eaddario
/

Dolphin3.0-Mistral-24B-GGUF

Text Generation

Model card Files Files and versions

Dolphin3.0-Mistral-24B-GGUF / Dolphin3.0-Mistral-24B-IQ4_NL.gguf

Commit History

Layer-wise quantization IQ4_NL

779b575
verified

eaddario commited on May 7

Experimental quantize+prune IQ4_NL

664d860
verified

eaddario commited on Mar 6

Generate IQ4_NL quant

34e53a5

eaddario commited on Feb 22