Get the app
← back to catalog · registered 2026-08-22 13:56

TomerGamerTV/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX

TomerGamerTV Qwen 4.2B multimodal second-order
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/TomerGamerTV%2FQwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX"
Response includes
  • classification m3
  • files 9
  • hub_downloads_all_time 1,878
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m3
Sibling qwen models · same method
 GET/methods/m3
What "m3" means · taxonomy
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
M1 Direct removal →
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)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
2K
221 last 30d - stable
Likes
2
Model age
6mo ago
created 2026-03-17
Downloads over time
Now2K→from212↑822%
1257931.5K2.1K212 on Mar 182K on Oct 12MarAprMayJunJulAugSepOct
Mar 18 → Oct 12 · 70 snapshots · spans 208 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING↓ 455 this lineage
TomerGamerTV/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX↓ 221

Metadata

License
apache-2.0
Languages
en zh
Tags
mlx safetensors qwen3_5 unsloth heretic uncensored abliterated fine tune creative creative writing fiction writing plot generation

Related

Same base model
mradermacher/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-GGUF 5K mradermacher/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-i1-GGUF 2K avan-ag/Qwen3.5-4B-Uncensored-MLX-4bit 574 xv1rcn/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX-4bit 379 xv1rcn/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX-8bit 201
Total size
2.20 GB
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-17 11:15
Source huggingface.co/TomerGamerTV/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX ↗ Base model DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING →

Files by quantization

Auxiliary files 9 files 2.22 GB
model.safetensors 2.20 GB 0dfd6217 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 79.1 KB e28a031a download
chat_template.jinja 7.78 KB 5a663a52 download
config.json 2.95 KB 1270ab05 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.20 KB ed66aa5e download
tokenizer_config.json 1.15 KB 040f6e4b download
generation_config.json 115 B affcdf18 download

README current version from Hugging Face

language:

  • en
  • zh
    license: apache-2.0
    tags:
  • unsloth
  • heretic
  • uncensored
  • abliterated
  • fine tune
  • creative
  • creative writing
  • fiction writing
  • plot generation
  • sub-plot generation
  • story generation
  • scene continue
  • storytelling
  • fiction story
  • science fiction
  • romance
  • all genres
  • story
  • writing
  • vivid prosing
  • vivid writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases
  • mlx
    library_name: mlx
    pipeline_tag: image-text-to-text
    base_model: DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

Qwen3.5-4B Claude-4.6 OS Auto Variable HERETIC UNCENSORED THINKING (MLX Q4)

This repository contains a Q4 MLX quantized conversion of:

DavidAU/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING

Changes in this repository:

  • Converted to MLX format
  • Q4 quantization applied
  • No training, finetuning, or architectural modifications

The original model, weights, and training remain unchanged.

Usage (MLX)

from mlx_lm import load, generate

model, tokenizer = load("TomerGamerTV/Qwen3.5-4B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MLX")

prompt = "Hello"
print(generate(model, tokenizer, prompt=prompt))

README history 3 versions

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

  1. 2026-03-17Update README.md6cf31441.2 KB
    Loading...
  2. 2026-03-17Upload folder using huggingface_hub76b3049551 B
    Loading...
  3. 2026-03-17initial commitcc598a928 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.

Get the app Browse the catalog
Open in Abliteration