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

dotwee/Huihui-Qwen3.5-27B-abliterated-MLX-4bit

dotwee Qwen 27B 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/dotwee%2FHuihui-Qwen3.5-27B-abliterated-MLX-4bit"
Response includes
  • classification m1
  • files 11
  • benchmarks 11 entries
  • hub_downloads_all_time 1,833
  • author_summary 1 models
  • readme_text full
Try next
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
2K
97 last 30d - cooling
Likes
1
Model age
7mo ago
created 2026-02-27
Downloads over time
Now1.9K→from197↑847%
1147531.4K2K197 on Feb 251.9K on Oct 11FebAprJunAugOct
Feb 25 → Oct 11 · 72 snapshots · spans 228 days

Benchmarks

Benchmark Score Source
Entertainment 1.6 UGI
Hazardous 2.9 UGI
Natural Intelligence 22.36 UGI
Political lean -24.2% UGI
Sensitive-Info 22.3 UGI
SocPol 2.4 UGI
UGI 44.87 UGI
Willingness (10) 9 UGI
W10-Adherence 10 UGI
W10-Direct 8 UGI
Writing 35.63 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.

huihui-ai/Huihui-Qwen3.5-27B-abliterated↓ 137,330 this lineage
dotwee/Huihui-Qwen3.5-27B-abliterated-MLX-4bit↓ 97

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 qwen qwen3.5 abliterated uncensored quantized 4-bit mlx-lm text-generation conversational

Related

Same base model
mradermacher/Huihui-Qwen3.5-27B-abliterated-GGUF 10K HeYujie/Qwen3.5-27B-abliterated-GGUF 4K mradermacher/Huihui-Qwen3.5-27B-abliterated-i1-GGUF 2K DevQuasar/huihui-ai.Huihui-Qwen3.5-27B-abliterated-GGUF 1K j-a-a-a-y/Huihui-Qwen3.5-27B-abliterated-AWQ-W4A16 231
Total size
14.1 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-02-27 18:36
Source huggingface.co/dotwee/Huihui-Qwen3.5-27B-abliterated-MLX-4bit ↗ Base model huihui-ai/Huihui-Qwen3.5-27B-abliterated →

Files by quantization

Auxiliary files 11 files 14.1 GB
model-00002-of-00003.safetensors 4.99 GB b77d6393 download
model-00001-of-00003.safetensors 4.96 GB 5dc2982c download
model-00003-of-00003.safetensors 4.14 GB 4dc468b0 download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 185 KB 512cabfb download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.82 KB d4dc5e5a download
README.md 2.12 KB f2f8122a download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.11 KB f57cfc38 download
generation_config.json 244 B 85b45ab4 download

README current version from Hugging Face

language: en
library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE
pipeline_tag: text-generation
base_model:

  • huihui-ai/Huihui-Qwen3.5-27B-abliterated
    tags:
  • qwen
  • qwen3.5
  • abliterated
  • uncensored
  • quantized
  • 4-bit
  • mlx
  • mlx-lm
    quantized_by: mlx_lm
    model_type: qwen3_5

Huihui-Qwen3.5-27B-abliterated-MLX-4bit

This repository contains an MLX-optimized 4-bit quantized conversion of
huihui-ai/Huihui-Qwen3.5-27B-abliterated for Apple Silicon inference.

The model was converted for mlx-lm text generation workflows.

Model details

  • Base model: huihui-ai/Huihui-Qwen3.5-27B-abliterated
  • Architecture family: Qwen3.5
  • Format: MLX safetensors shards
  • Quantization: affine 4-bit, group size 64
  • Observed average precision: ~4.501 bits/weight
  • Approximate on-disk size: ~12 GB

What is included

  • model-00001-of-00003.safetensors
  • model-00002-of-00003.safetensors
  • model-00003-of-00003.safetensors
  • model.safetensors.index.json
  • config.json
  • tokenizer.json
  • tokenizer_config.json
  • generation_config.json
  • chat_template.jinja

Usage with MLX

Install dependencies:

pip install -U mlx-lm

Quick generation:

mlx_lm.generate \
  --model dotwee/Huihui-Qwen3.5-27B-abliterated-MLX-4bit \
  --prompt "Write one short sentence about MLX." \
  --max-tokens 128

Chat mode:

mlx_lm.chat --model dotwee/Huihui-Qwen3.5-27B-abliterated-MLX-4bit

Notes and limitations

  • This artifact is intended for text generation with mlx-lm.
  • The upstream checkpoint is described as uncensored/abliterated and may produce
    sensitive, controversial, or unsafe outputs.
  • Use only in contexts where strict output review and moderation are possible.
  • For production or public-facing deployments, add downstream safety controls.

License

This release follows the upstream Qwen3.5 license and terms:
apache-2.0 (see license_link in model metadata).

Provenance

  • Upstream model: huihui-ai/Huihui-Qwen3.5-27B-abliterated
  • Converted with: mlx_lm convert
  • Conversion settings: --quantize --q-bits 4 --q-group-size 64

README history 3 versions

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

  1. 2026-02-27build(release): mlx huggingface release optimize weights into 4-bit mlx forma...5a72a392.1 KB
    Loading...
  2. 2026-02-27Update README.mdcb7a2f62.4 KB
    Loading...
  3. 2026-02-27Create README.md1358cb62.1 KB
    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