Skip to content

Frosty40

qwen38-mtp-head-qat-shrink-v1

Frosty40/qwen38-mtp-head-qat-shrink-v1

qwen38-mtp-head-qat-shrink-v1 is a machine learning model from Frosty40. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Research checkpoint: a multi-token-prediction (MTP) draft head for Qwen/Qwen3.8-27B, from OmniSpace's speculative-decoding experiments. Not a production release. Kept public so the runs can be reproduced.

Downloads · 30 days

0

Access

Public

Updated Nov 18, 2026

Parameters

102M

352 MB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors352 MB · 100%

Parameter types

How the weights are stored.

U3273.4M · 72%

Base models

License
apache-2.0
Created
Aug 23, 2026
Updated
Nov 18, 2026