← back to catalog · registered 2026-11-15 20:03

brainworkup/Qwen3.8-27B-Ultimate-Heretic-Uncensored-oQ2e-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-oQ2e-mtp"
Response includes
  • classification m3
  • files 14
  • 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
106
Likes
0
Model age
6d ago
created 2026-11-15
Downloads over time
Now 106 → from 0 ↑ 0%
03978117 0 on Nov 15 106 on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 days

Metadata

Tags
mlx safetensors qwen3_5 oq quantized mtp 2-bit region:us

Related

Total size
11.0 GB
Files
14
Quantizations
1
Registered
2026-11-15 20:03
Last updated on HF
2026-11-15 20:00

Files by quantization

Auxiliary files 14 files 11.0 GB
model-00002-of-00003.safetensors 4.68 GB 7eab9d7e download
model-00001-of-00003.safetensors 4.68 GB f0fe2712 download
model-00003-of-00003.safetensors 1.65 GB 79e8174f 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 822b25aa download
config.json 74.9 KB 817160e4 download
oq_imatrix_report.json 30.5 KB 5daf8253 download
tokenizer_config.json 8.48 KB 1a7e62d0 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.15 KB 69ddea68 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-oQ2e-mtp

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

The effective average is 3.406 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 2-bit, group 64 12.387B 44.588% 3.605 GiB 2.50
Affine 3-bit, group 128 10.453B 37.627% 3.955 GiB 3.25
Affine 3-bit, group 64 1.271B 4.576% 0.518 GiB 3.50
Affine 4-bit, group 64 0.372B 1.340% 0.195 GiB 4.50
Affine 5-bit, group 64 2.781B 10.012% 1.781 GiB 5.50
BF16 0.516B 1.857% 0.961 GiB 16.00
Total 27.781B 100% 11.015 GiB 3.406

Storage Breakdown

Component Logical weights Storage
Language model 26.896B 10.591 GB / 9.864 GiB
Vision 0.461B 0.921 GB / 0.858 GiB
MTP head 0.425B 0.314 GB / 0.293 GiB
Total 27.781B 11.827 GB / 11.015 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-oQ2e-mtp via oMLX bc28ea1 1.1 KB
    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