CoolFace
Modelpublic

CompressedMichael/Qwen3-VL-30B-A3B-Instruct-SmoothQuant-W8A8

sourceHugging Faceapache-2.0updated 13d agoView on Hugging Face
0likes47downloads
root
file.gitattributes2 KBdownload
fileadded_tokens.json707 Bdownload
fileartifact_audit.json668 Bdownload
filechat_template.jinja5 KBdownload
fileconfig.json10 KBdownload
filegeneration_config.json213 Bdownload
fileLICENSE11 KBdownload
filemerges.txt1.6 MBdownload
filemodel-00001-of-00009.safetensors3.73 GBdownload
filemodel-00002-of-00009.safetensors3.72 GBdownload
filemodel-00003-of-00009.safetensors3.73 GBdownload
filemodel-00004-of-00009.safetensors3.73 GBdownload
filemodel-00005-of-00009.safetensors3.72 GBdownload
filemodel-00006-of-00009.safetensors3.73 GBdownload
filemodel-00007-of-00009.safetensors3.72 GBdownload
filemodel-00008-of-00009.safetensors3.42 GBdownload
filemodel-00009-of-00009.safetensors593.5 MBdownload
filemodel.safetensors.index.json3.9 MBdownload
filemodeling_qwen3_vl_moe_quantized.py4 KBdownload
fileNOTICE402 Bdownload
filepreprocessor_config.json784 Bdownload
filequantization_run.json3 KBdownload
fileREADME.md4 KBdownload
filerecipe.yaml750 KBdownload
filespecial_tokens_map.json613 Bdownload
filetokenizer_config.json5 KBdownload
filetokenizer.json10.9 MBdownload
filevalidation.json646 Bdownload
filevideo_preprocessor_config.json817 Bdownload
filevocab.json2.6 MBdownload

CompressedMichael/Qwen3-VL-30B-A3B-Instruct-SmoothQuant-W8A8 · main · files are served by the source, never re-hosted here