Skip to content

dusterbloom

Qwen3.8-27B-MTP-4bit-g64

dusterbloom/Qwen3.8-27B-MTP-4bit-g64

Qwen3.8-27B-MTP-4bit-g64 is a machine learning model from dusterbloom. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

This directory is an OPTIONAL editable path (benchmark.json optionalEditablePaths). It carries MTP head weights only when a submission declares "source": "inbranch" in ../mtp-head.manifest.json. The checked-in declara…

Downloads · 30 days

41

38% of all-time downloads

All-time downloads

107

Public

Parameters

66.4M

239 MB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors239 MB · 100%

Parameter types

How the weights are stored.

U3253.1M · 80%

Type
qwen3_5_mtp
Created
Aug 15, 2026
Updated
Aug 15, 2026