← back to catalog · registered 2026-11-15 19:03

brainworkup/Qwen3.8-27B-Ultimate-Heretic-Uncensored-oQ8e-mtp

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/brainworkup%2FQwen3.8-27B-Ultimate-Heretic-Uncensored-oQ8e-mtp"
Response includes
  • classification m3
  • files 17
  • author_summary 10 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · 30-day
86
Likes
0
Model age
6d ago
created 2026-11-15
Downloads over time
Now 86 → from 0 ↑ 0%
0326395 0 on Nov 15 86 on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 days

Metadata

Tags
mlx safetensors qwen3_5 oq quantized mtp 8-bit region:us

Related

Total size
27.9 GB
Files
17
Quantizations
1
Registered
2026-11-15 19:03
Last updated on HF
2026-11-15 18:47

Files by quantization

Auxiliary files 17 files 28.0 GB
model-00005-of-00006.safetensors 4.71 GB c3da2f6b download
model-00001-of-00006.safetensors 4.69 GB 529b5fdb download
model-00004-of-00006.safetensors 4.69 GB de8af69b download
model-00002-of-00006.safetensors 4.66 GB 1a308fda download
model-00003-of-00006.safetensors 4.66 GB 571025ee download
model-00006-of-00006.safetensors 4.53 GB ddf13d60 download
tokenizer.json 19.1 MB 6f32ce20 download
vocab.json 6.41 MB 0aa0ce06 download
chat_template.jinja 246 KB 485b7fc6 download
model.safetensors.index.json 207 KB 525b6a39 download
oq_imatrix_report.json 30.5 KB 692337df download
tokenizer_config.json 8.48 KB 1a7e62d0 download
config.json 3.89 KB 9334c224 download
.gitattributes 1.53 KB 52373fe2 download
README.md 918 B 84449bf8 download
preprocessor_config.json 390 B 2ea84a43 download
generation_config.json 214 B 0bc3addd download

README current version from Hugging Face


library_name: mlx
tags:

  • mlx
  • oq
  • quantized
  • mtp

Qwen3.8-27B-Ultimate-Heretic-Uncensored-oQ8e-mtp

This model was quantized using oQ (oMLX v0.8.0rc1) mixed-precision quantization.

The effective average is 8.639 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 8-bit, group 64 27.266B 98.143% 26.980 GiB 8.50
BF16 0.516B 1.857% 0.961 GiB 16.00
Total 27.781B 100% 27.941 GiB 8.639

Storage Breakdown

Component Logical weights Storage
Language model 26.896B 28.579 GB / 26.617 GiB
Vision 0.461B 0.921 GB / 0.858 GiB
MTP head 0.425B 0.500 GB / 0.466 GiB
Total 27.781B 30.001 GB / 27.941 GiB

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-15 Upload Qwen3.8-27B-Ultimate-Heretic-Uncensored-oQ8e-mtp via oMLX dbb26aa 918 B
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration