CoolFace
Modelpublic

Twu31/Qwen3.8-27B-AWQ-INT4-MTP-LowLatency

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face
5likes5.3kdownloads
root
revisiongptq-llmcompressorawq-llmcompressormtp-int4-autoroundlm-head-int4main
file.gitattributes2 KBdownload
filechat_template.jinja9 KBdownload
fileconfig.json21 KBdownload
filegeneration_config.json202 Bdownload
filemerges.txt3.2 MBdownload
filemodel_extra_tensors.safetensors810.1 MBdownload
filemodel-00001-of-00007.safetensors2.99 GBdownload
filemodel-00002-of-00007.safetensors2.98 GBdownload
filemodel-00003-of-00007.safetensors2.98 GBdownload
filemodel-00004-of-00007.safetensors3.00 GBdownload
filemodel-00005-of-00007.safetensors666.9 MBdownload
filemodel-00006-of-00007.safetensors2.37 GBdownload
filemodel-lmhead-int8.safetensors1.20 GBdownload
filemodel.safetensors.index.json194 KBdownload
filepreprocessor_config.json390 Bdownload
fileprocessor_config.json1 KBdownload
filequantization_config.json16 KBdownload
fileREADME.md28 KBdownload
filetokenizer_config.json18 KBdownload
filetokenizer.json12.2 MBdownload
filevocab.json6.4 MBdownload

Twu31/Qwen3.8-27B-AWQ-INT4-MTP-LowLatency · main · files are served by the source, never re-hosted here