← back to catalog · registered 2026-11-19 06:04

mlx-community/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-oQ6h-mtp

mlx-community Deepseek 9B
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/mlx-community%2FDeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-oQ6h-mtp"
Response includes
  • classification m3
  • files 17
  • author_summary 211 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
145
Likes
0
Model age
3d ago
created 2026-11-19
Downloads over time
Now 145 → from 0 ↑ 0%
053106160 0 on Nov 19 145 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

Metadata

Tags
mlx safetensors qwen3_5 oq quantized mtp 6-bit region:us

Related

Total size
8.06 GB
Files
17
Quantizations
1
Registered
2026-11-19 06:04
Last updated on HF
2026-11-19 06:02

Files by quantization

Auxiliary files 17 files 8.08 GB
model-00002-of-00003.safetensors 4.75 GB 31d74485 download
model-00001-of-00003.safetensors 2.62 GB 3c314bb2 download
model-00003-of-00003.safetensors 707 MB 01b8b134 download
tokenizer.json 19.1 MB a5cd9732 download
vocab.json 4.99 MB b94df23d download
model.safetensors.index.json 145 KB 59aa09e7 download
config.json 36.6 KB 5fc38579 download
chat_template.jinja 8.53 KB 3318462a download
oq_imatrix_report.json 3.27 KB cc218a0e download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.29 KB a9804dd9 download
tokenizer_config.json 1.19 KB 0bf8509e download
README.md 1.11 KB 71dbbfbf download
added_tokens.json 904 B 9955816d download
special_tokens_map.json 876 B fca0ded4 download
preprocessor_config.json 781 B 484b50c4 download
generation_config.json 142 B 79b5436a download

README current version from Hugging Face


library_name: mlx
tags:

  • mlx
  • oq
  • quantized
  • mtp

DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-oQ6h-mtp

[!NOTE]
Updated 2026-11-19: Re-quantized with oMLX v0.8.0. Please re-download if you have an earlier copy.

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

The effective average is 16.288 bits/weight for the complete checkpoint.

Quantization and Bit Distribution

Storage format Logical weights Share of total Tensor storage Effective bits/weight
Affine 6-bit, group 64 2.223B 52.301% 1.682 GiB 6.50
Affine 8-bit, group 64 0.021B 0.493% 0.021 GiB 8.50
BF16 0.600B 14.117% 1.118 GiB 16.00
U32 1.406B 33.088% 5.239 GiB 32.00
Total 4.250B 100% 8.060 GiB 16.288

Storage Breakdown

Component Logical weights Storage
Language model 3.551B 7.499 GB / 6.984 GiB
Vision 0.456B 0.912 GB / 0.849 GiB
MTP head 0.243B 0.243 GB / 0.226 GiB
Total 4.250B 8.654 GB / 8.060 GiB

README history 1 version

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

  1. 2026-11-19 Upload DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-oQ6h-mtp via oMLX f26055b 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