safetensors BF16

A quantized build of the model Qwen3.8-27B.

Publisher
Qwen (Alibaba)
Source platform
HUGGINGFACE
Quantization
BF16
Revision
1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
Updated
2026-09-26
Total size
51.75 GB

File list

Paths and sizes come from the release page; a missing size shows "not provided".

File pathSize
model-00001-of-00018.safetensors3.69 GB
model-00002-of-00018.safetensors2.83 GB
model-00003-of-00018.safetensors2.37 GB
model-00004-of-00018.safetensors3.72 GB
model-00005-of-00018.safetensors1.96 GB
model-00006-of-00018.safetensors3.71 GB
model-00007-of-00018.safetensors1.96 GB
model-00008-of-00018.safetensors3.71 GB
model-00009-of-00018.safetensors1.96 GB
model-00010-of-00018.safetensors3.71 GB
model-00011-of-00018.safetensors1.96 GB
model-00012-of-00018.safetensors3.71 GB
model-00013-of-00018.safetensors1.96 GB
model-00014-of-00018.safetensors3.71 GB
model-00015-of-00018.safetensors1.96 GB
model-00016-of-00018.safetensors3.71 GB
model-00017-of-00018.safetensors1.96 GB
model-00018-of-00018.safetensors3.16 GB

Linked benchmarks

Only benchmarks tied to this exact release are listed.

No linked benchmarks.

Deployment guidance

This site doesn't guess whether or how this build runs on your machine. General local-deployment tutorials are linked below; if a link or data on this page is wrong, please tell us.