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

mlx-community/Huihui-Qwen3.6-27B-abliterated-4.5bit-msq

mlx-community Qwen 3.7B 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-Qwen3.6-27B-abliterated-4.5bit-msq"
Response includes
  • classification m1
  • files 21
  • benchmarks 11 entries
  • hub_downloads_all_time 647
  • 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
647
53 last 30d - cooling
Likes
3
Model age
5mo ago
created 2026-04-23
Downloads over time
Now666→from69↑865%
3926849772669 on Apr 22666 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 1.2 UGI
Hazardous 4.7 UGI
Natural Intelligence 33.16 UGI
Political lean -20.0% UGI
Sensitive-Info 26.98 UGI
SocPol 2.9 UGI
UGI 27.15 UGI
Willingness (10) 2.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 4 UGI
Writing 42.47 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/Qwen3.6-27B this lineage
mlx-community/Huihui-Qwen3.6-27B-abliterated-4.5bit-msq↓ 53

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored conversational base_model:Qwen/Qwen3.6-27B base_model:quantized:Qwen/Qwen3.6-27B 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/Qwen3.6-27B-Uncensored-HauhauCS-Aggressive 49K HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced 25K huihui-ai/Huihui-Qwen3.6-27B-abliterated-MTP-GGUF 22K AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-BF16 10K huihui-ai/Huihui-Qwen3.6-27B-abliterated 4K
Total size
15.8 GB
Files
21
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-23 17:49
Source huggingface.co/mlx-community/Huihui-Qwen3.6-27B-abliterated-4.5bit-msq ↗ Base model Qwen/Qwen3.6-27B ↗

Files by quantization

Auxiliary files 21 files 15.8 GB
model-00001-of-00004.safetensors 5.00 GB 9b744c7d download
model-00002-of-00004.safetensors 4.97 GB fdd270c1 download
model-00003-of-00004.safetensors 4.55 GB 064720cb download
model-00004-of-00004.safetensors 1.26 GB 932d7d02 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 228 KB 4783a758 download
LICENSE 11.1 KB 1d5180a4 download
config.json 10.5 KB 8f235eb1 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 785 B ad53bb82 download
quant_recipe.json 455 B d3a0dc48 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 51.0 B 3a6d4256 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/Qwen3.6-27B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.6-27B
    tags:
  • abliterated
  • uncensored

Huihui-Qwen3.6-27B-abliterated — MLX 4.5 BPW

Mixed-precision MLX quantization of huihui-ai/Huihui-Qwen3.6-27B-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: 4.53 bits per weight
  • Method: MLX Smart Quantize (MSQ)

README history 1 version

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

  1. 2026-04-23Add files using upload-large-folder toolb3e0742785 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