Downloads · 30 days
27
29% of all-time downloads
Qwen3.8-27B-MTP-head-q4mlp
Lie24/Qwen3.8-27B-MTP-head-q4mlp
Qwen3.8-27B-MTP-head-q4mlp is a machine learning model from Lie24. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Byte-identical mirror of p0ly31/Qwen3.8-27B-MTP-head-q4mlp @ 58224b03 (author: polymorf, mlxfast Qwen-MTP challenge — full credit to them; see the 45c257f1 submission note and its V5 addendum for the recipe and receip…
All-time downloads
94
Public
Parameters
314M
946 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors946 MB · 100%
Parameter types
How the weights are stored.
U32159M · 51%
Model card
From the Hugging Face model README
Qwen3.8-27B MTP head, fc+MLP affine-4 g64 + 3-bit draft_lm_head (mirror)
Byte-identical mirror of p0ly31/Qwen3.8-27B-MTP-head-q4mlp @ 58224b03
(author: polymorf, mlxfast Qwen-MTP challenge — full credit to them; see the
45c257f1 submission note and its V5 addendum for the recipe and receipts).
Mirrored for fetch-time availability of a declared-head submission.
- model.safetensors: 945,903,182 bytes, 26 tensors
- file sha256: 608073cac12528478788b22d1d68a48f0874d057847fbe8abf5c8225349fb6ae
- runner tree digest: b6983fa2a426d3aa0594b7dfe75768c8ad62e0607ae6549370507c11feee9d71
- Type
- qwen3_5_mtp
- Created
- Aug 15, 2026
- Updated
- Aug 15, 2026