Downloads · 30 days
53
31% of all-time downloads
Ted17846578368756/qwen38-uncensored-mlx4b-mtp
qwen38-uncensored-mlx4b-mtp is a image-text-to-text model from Ted17846578368756. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Uncensored Qwen3.8-27B (orcarouter abliteration lineage), MLX uniform 4-bit, with the native MTP speculative-decoding head grafted back in.
Downloads · 30 days
53
31% of all-time downloads
All-time downloads
173
Public
Parameters
27.8B
16.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.9 GB · 100%
How the weights are stored.
U3226.9B · 97%
From the Hugging Face model README
Uncensored Qwen3.8-27B (orcarouter abliteration lineage), MLX uniform 4-bit, with the native MTP speculative-decoding head grafted back in.
orcarouter/Qwen3.8-27B-Uncensored-MLX (root files = 4-bit).
Shard bytes are unchanged (hardlink-verified); only filenames/index were
rewritten from -of-00003 to -of-00004.orcarouter/Qwen3.8-27B-Uncensored-MLX mtp/model.safetensors
sidecar (15 BF16 tensors), re-indexed as language_model.mtp.* in
model-00004-of-00004.safetensors - the embedded layout oMLX native MTP
expects (same as Jundot/Qwen3.8-27B-oQ4e-mtp).mlx-community/Qwen3.8-27B-4bit (identical LFS objects to the orcarouter repo).SHA256SUMS.json: full sha256 of the new MTP shard; body shards referenced
by their upstream LFS sha256.oMLX: add to a scanned model dir, load, check engine log for
Lightning MTP enabled ... (checkpoint layout: mtp.). Depth 1 (prose) or 2
(code); depth 3 gains nothing on this architecture.
Requires oMLX with indexed-sidecar/MTP detection (>=0.6.x; issues #1944/#1962/#2220 fixed).
License: Apache-2.0, inherited from Qwen/Qwen3.8-27B.