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

pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit

pixelkaiser Qwen 27B 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/pixelkaiser%2FHuihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit"
Response includes
  • classification m1
  • files 18
  • hub_downloads_all_time 647
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=pixelkaiser
All 4 models by pixelkaiser
 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
58 last 30d - cooling
Likes
0
Model age
2mo ago
created 2026-07-17
Downloads over time
Now670→from72↑831%
4227150173072 on Jul 15670 on Oct 11JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 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.

huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated↓ 717 this lineage
pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit↓ 58

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5 qwen3_6 4-bit abliterated image-text-to-text conversational base_model:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated base_model:quantized:huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated license:apache-2.0 region:us

Related

Other by pixelkaiser
Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP 676 Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 206 Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-MTP 132
Same base model
mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-i1-GGUF 1K mradermacher/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-GGUF 1K pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP 676 sakamakismile/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-NVFP4 353 pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-LMStudio-MTP-Drafter-BF16 206
Total size
15.0 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-17 18:15
Source huggingface.co/pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit ↗ Base model huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated →

Files by quantization

Auxiliary files 18 files 15.0 GB
model-00003-of-00003.safetensors 4.99 GB 6eedfe7a download
model-00002-of-00003.safetensors 4.99 GB 2b2e16c9 download
model-00001-of-00003.safetensors 4.98 GB 44be9aa6 download
tokenizer.json 19.1 MB 06b95093 download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 213 KB 05a3a3a1 download
merge_verify_report.json 35.5 KB cd0fc3ee download
chat_template.jinja 7.58 KB a8755d82 download
config.json 4.91 KB 5179c41d download
README.md 1.56 KB 6f460f8f download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.14 KB 1d134cd2 download
weight_check_report.json 1.05 KB d02433a6 download
processor_config.json 991 B 8f29fe38 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 213 B c20033f9 download
configuration.json 51.0 B 3a6d4256 download

README current version from Hugging Face

license: apache-2.0
base_model: huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated
base_model_relation: quantized
library_name: mlx
pipeline_tag: image-text-to-text
tags:

  • mlx
  • qwen3_6
  • 4-bit
  • abliterated

Huihui ThinkingCap Qwen3.6 27B Abliterated — MLX 4-bit

MLX affine 4-bit (group size 64) conversion of huihui-ai/Huihui-ThinkingCap-Qwen3.6-27B-abliterated, pinned to revision 44f63da.

Converted with mlx-vlm 0.6.5 and mlx 0.32.0. A bounded generation smoke test passed after conversion.

Runtime recommendation

For MTP, use pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit-oMLX-MTP with oMLX Native MTP. oMLX is the recommended MTP runtime for this model because it provides the faster, more mature integrated path.

LM Studio users should load this target-only repository with MTP disabled. LM Studio 0.4.19+2 with MLX runtime 1.10.1 does not currently support speculative draft models for batched vision models.

mlx_vlm.generate --model pixelkaiser/Huihui-ThinkingCap-Qwen3.6-27B-abliterated-MLX-4bit --prompt "Hello" --max-tokens 256

This is an abliterated model with reduced safety behavior. Review the upstream model card before use.

README history 2 versions

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

  1. 2026-07-17Recommend oMLX for MTP5e1728e1.6 KB
    Loading...
  2. 2026-07-17Add files using upload-large-folder tool193bdfd1 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