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

hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16

hawhyhb Qwen 35B MoE 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/hawhyhb%2FQwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16"
Response includes
  • classification m3
  • files 18
  • hub_downloads_all_time 2,847
  • 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
3K
526 last 30d - stable
Likes
3
Model age
2mo ago
created 2026-07-29
Downloads over time
Now3K→from594↑409%
4731.4K2.3K3.3K594 on Jul 293K on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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.

llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved↓ 749 this lineage
hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16↓ 526

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5_moe mtplx apple-silicon qwen qwen3.6 uncensored heretic speculative-decoding vision multimodal

Related

Same base model
SC117/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-APEX-GGUF 71K llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GGUF 31K llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GPTQ-Int4 19K mradermacher/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-i1-GGUF 4K mradermacher/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-GGUF 2K
Total size
20.6 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-29 08:25
Source huggingface.co/hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16 ↗ Base model llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved →

Files by quantization

Auxiliary files 18 files 20.6 GB
model-00002-of-00004.safetensors 5.00 GB 0410f61d download
model-00003-of-00004.safetensors 5.00 GB 6b1a0860 download
model-00001-of-00004.safetensors 4.98 GB 0400902d download
model-00004-of-00004.safetensors 3.19 GB e161b2e9 download
mtp.safetensors 1.57 GB 84fe0f4a download
vision_tower.safetensors 852 MB 50072e8e download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 200 KB 65e313e2 download
config.json 20.0 KB da949670 download
chat_template.jinja 11.5 KB 03a040a2 download
mtplx_runtime.json 4.34 KB b43e6420 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.46 KB b5386ac3 download
processor_config.json 1.28 KB a3be3e79 download
tokenizer_config.json 1.24 KB 0b282af8 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 226 B 2dd033e0 download

README current version from Hugging Face

library_name: mlx
license: apache-2.0
pipeline_tag: image-text-to-text
tags:

  • mlx
  • mtplx
  • apple-silicon
  • qwen
  • qwen3.6
  • uncensored
  • heretic
  • speculative-decoding
  • vision
  • multimodal
    base_model: llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

Qwen3.6-35B-A3B Uncensored Heretic · MTPLX 4-bit FP16 (+ Vision)

Local MTPLX forge of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved, with the vision tower restored after 4-bit body conversion.

  • Body: MLX affine 4-bit (group size 64)
  • Non-quantized leaves / MTP floats: FP16 (M1/M2 friendly)
  • Vision: FP16 vision_tower.safetensors (grafted from BF16 source model.visual.*)
  • Includes mtp.safetensors + mtplx_runtime.json (verified on Apple Silicon)
  • Approx size: ~21GB on disk

Run with MTPLX

mtplx start --model hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16
# or local path
mtplx start --model ~/Documents/MTPLX/models/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16
# API only
mtplx quickstart --model hawhyhb/Qwen3.6-35B-A3B-Uncensored-Heretic-MTPLX-4bit-FP16 --profile sustained --port 8000

Vision works via OpenAI-compatible image_url content parts (no llama.cpp mmproj).

Notes

  • First forge pass dropped the vision tower; this revision grafts it back and ships preprocessor_config.json / processor_config.json / video_preprocessor_config.json.
  • Uncensored Heretic text behavior comes from the source repo; use responsibly.

README history 2 versions

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

  1. 2026-07-29Publish MTPLX forged model0ff77a41.5 KB
    Loading...
  2. 2026-07-29Upload MTPLX 4-bit FP16 forged Heretic Qwen3.6-35B-A3B7faea35795 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