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

mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit

mlx-community Qwen 27B 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-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 30,652
  • 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
31K
2K last 30d - cooling
Likes
22
Descendants
1
in 1 direct fork
Model age
7mo ago
created 2026-03-14
Downloads over time
Now31.7K→from444↑7,050%
011.6K23.3K34.9K444 on Mar 1631.7K on Oct 12MarAprMayJunJulAugSepOct
Mar 16 → Oct 12 · 72 snapshots · spans 210 days

Genealogy 1 direct fork

Full fork graph →

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

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled this lineage
mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit↓ 2,399 1 fork
dream-vault-community/Qwen3.5-27B-4bit-Abliterated↓ 150

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5 image-text-to-text abliterated uncensored Claude reasoning chain-of-thought Dense mlx conversational

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
huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated 319 mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-6bit 188 groxaxo/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-exl3-6bpw 25 Bagaee/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated 15 Daniil228hdchh/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated 15
Total size
15.0 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-14 20:07
Source huggingface.co/mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit ↗ Base model Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled ↗

Files by quantization

Auxiliary files 11 files 15.0 GB
model-00003-of-00003.safetensors 4.99 GB b87f06d1 download
model-00002-of-00003.safetensors 4.99 GB a11f71f8 download
model-00001-of-00003.safetensors 4.98 GB 7eb2e66c download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 213 KB b70b9458 download
config.json 4.54 KB 52914550 download
chat_template.jinja 3.95 KB 609532bf download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.14 KB aeb7593d download
README.md 971 B 3d5cf7a4 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
    tags:
  • abliterated
  • uncensored
  • Claude
  • reasoning
  • chain-of-thought
  • Dense
  • mlx

mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit

This model was converted to MLX format from huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated using mlx-vlm version 0.4.0.
Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 1 version

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

  1. 2026-03-14Upload folder using huggingface_hub75bfb86971 B
    Loading...

Discussions 1 thread

  1. 2026-04-01MLX conversions have wrong tensor shapes (5B params instead of 27B)open1 💬#1
    Loading...

Continue on Hugging Face →

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