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

mlx-community/Huihui-Qwen3.6-35B-A3B-abliterated-4.4bit-msq

mlx-community Qwen 4.7B MoE multimodal
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%2FHuihui-Qwen3.6-35B-A3B-abliterated-4.4bit-msq"
Response includes
  • classification m1
  • files 21
  • benchmarks 11 entries
  • hub_downloads_all_time 2,524
  • author_summary 207 models
  • readme_text full
Try next
GET/models?author=mlx-community
All 207 models by mlx-community
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
3K
208 last 30d - cooling
Likes
6
Model age
5mo ago
created 2026-04-18
Downloads over time
Now2.6K→from138↑1,775%
169541.9K2.8K138 on Apr 222.6K on Oct 11AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 0 UGI
Natural Intelligence 25.43 UGI
Political lean -19.6% UGI
Sensitive-Info 14.03 UGI
SocPol 2.6 UGI
UGI 16.02 UGI
Willingness (10) 2 UGI
W10-Adherence 0 UGI
W10-Direct 4 UGI
Writing 35.83 UGI

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.

Qwen/Qwen3.6-35B-A3B this lineage
mlx-community/Huihui-Qwen3.6-35B-A3B-abliterated-4.4bit-msq↓ 208

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5_moe image-text-to-text abliterated uncensored conversational base_model:Qwen/Qwen3.6-35B-A3B base_model:quantized:Qwen/Qwen3.6-35B-A3B license:apache-2.0 endpoints_compatible 4-bit

Related

Other by mlx-community
Qwen3.8-27B-Uncensored-OptiQ-4bit 16K Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit 7K Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp 5K Josiefied-Qwen3-4B-abliterated-v1-4bit 4K Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit 4K
Same base model
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 854K Bahushruth/Qwen3.6-35B-A3B-abliterated-v4 475K huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF 107K Lord-H4D3ZS/Qwen3.8-Distill-35B-A3B-Coder-Abliterated 21K kyaky/Qwen3.6-35B-A3B-Uncensored-NVFP4 18K
Total size
19.7 GB
Files
21
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-18 17:57
Source huggingface.co/mlx-community/Huihui-Qwen3.6-35B-A3B-abliterated-4.4bit-msq ↗ Base model Qwen/Qwen3.6-35B-A3B ↗

Files by quantization

Auxiliary files 21 files 19.8 GB
model-00003-of-00005.safetensors 4.90 GB ea7553c7 download
model-00001-of-00005.safetensors 4.90 GB b1f24346 download
model-00002-of-00005.safetensors 4.89 GB a236148b download
model-00004-of-00005.safetensors 4.54 GB e66fc53b download
model-00005-of-00005.safetensors 515 MB 145818a7 download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
merges.txt 3.20 MB a494e019 download
model.safetensors.index.json 209 KB 61363695 download
config.json 70.3 KB e46aa643 download
chat_template.jinja 7.58 KB a8755d82 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
tokenizer_config.json 1.11 KB a068e246 download
README.md 1003 B 11d58c32 download
quant_recipe.json 578 B 7462da3e download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 202 B 023756cf download
configuration.json 58.0 B d24dba94 download
.gitignore 18.0 B 62687331 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.6-35B-A3B
    tags:
  • abliterated
  • uncensored

Huihui-Qwen3.6-35B-A3B-abliterated — MLX 4.4 BPW

Mixed-precision MLX quantization of huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated, quantized with MLX Smart Quantize (MSQ) — my own sensitivity-based mixed-precision quantization method for Apple Silicon. It measures per-layer NMSE and assigns optimal bit widths automatically, combining architecture knowledge with measured data.

Details

  • Type: Vision (VLM)
  • Average: 4.39 bits per weight
  • Method: MLX Smart Quantize (MSQ)
  • AWQ scaling: applied to 50 groups

Evaluation

Benchmark Score Samples
MMLU 82.1% 285
HellaSwag 91.5% 200
GSM8K 86.5% 200

README history 1 version

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

  1. 2026-04-18Add files using upload-large-folder toolac8c4a61003 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