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

AITRADER/Huihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX

AITRADER Qwen 35B 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/AITRADER%2FHuihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX"
Response includes
  • classification m1
  • files 27
  • benchmarks 11 entries
  • hub_downloads_all_time 2,793
  • author_summary 30 models
  • readme_text full
Try next
GET/models?author=AITRADER
All 30 models by AITRADER
 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
64 last 30d - cooling
Likes
2
Model age
7mo ago
created 2026-02-27
Downloads over time
Now2.8K→from251↑1,021%
1231.1K2.1K3.1K251 on Feb 252.8K on Oct 11FebAprJunAugOct
Feb 25 → Oct 11 · 72 snapshots · spans 228 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 0.8 UGI
Hazardous 4.1 UGI
Natural Intelligence 24.97 UGI
Political lean -20.7% UGI
Sensitive-Info 20.98 UGI
SocPol 2.1 UGI
UGI 23.15 UGI
Willingness (10) 2.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 4 UGI
Writing 37 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/Qwen3.5-35B-A3B this lineage
AITRADER/Huihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX↓ 64

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5_moe image-text-to-text abliterated uncensored mlx conversational base_model:Qwen/Qwen3.5-35B-A3B base_model:finetune:Qwen/Qwen3.5-35B-A3B license:apache-2.0 endpoints_compatible

Related

Other by AITRADER
Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated-mlx-mxfp8 298 Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX 263 Huihui-Qwen3-Coder-Next-abliterated-mlx-8Bit 251 gemma-4-31B-Claude-Opus-Distill-abliterated-mlx-mxfp8 211 Qwen2.5-VL-32B-Instruct-abliterated-mlx-fp16 203
Same base model
HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive 126K huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated 2K kataguru/Qwen3.5-35B-A3B-Jackripper-v1.0-Uncensored-GGUF 987 Unrestricted/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive 827 amarck/Qwen3.5-35B-A3B-abliterated-GGUF 475
Total size
65.4 GB
Files
27
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-02-28 21:15
Source huggingface.co/AITRADER/Huihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX ↗ Base model Qwen/Qwen3.5-35B-A3B ↗

Files by quantization

Auxiliary files 27 files 65.4 GB
model-00001-of-00014.safetensors 4.98 GB f32f9e55 download
model-00013-of-00014.safetensors 4.71 GB fb2565b4 download
model-00005-of-00014.safetensors 4.71 GB ad2f8326 download
model-00009-of-00014.safetensors 4.71 GB e5cdd7f9 download
model-00010-of-00014.safetensors 4.70 GB 792ba2fd download
model-00006-of-00014.safetensors 4.70 GB ce7425c5 download
model-00012-of-00014.safetensors 4.70 GB d3877bef download
model-00011-of-00014.safetensors 4.70 GB e9694af7 download
model-00007-of-00014.safetensors 4.70 GB 42f65bea download
model-00004-of-00014.safetensors 4.70 GB 04c7ce05 download
model-00002-of-00014.safetensors 4.70 GB c60eea44 download
model-00008-of-00014.safetensors 4.70 GB 053330a5 download
model-00003-of-00014.safetensors 4.70 GB 07a2129e download
model-00014-of-00014.safetensors 4.01 GB d4c5d472 download
tokenizer.json 19.1 MB 87a7830d download
vocab.json 6.41 MB 0aa0ce06 download
model.safetensors.index.json 104 KB d6f9781b download
chat_template.jinja 7.57 KB a585dec8 download
chat_template-vl-think.jinja 5.24 KB 3e446f2f download
config.json 3.52 KB b78a28d6 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.11 KB a068e246 download
README.md 802 B cb466dd0 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 244 B 5ff346d6 download

README current version from Hugging Face

library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
base_model:

  • Qwen/Qwen3.5-35B-A3B
    tags:
  • abliterated
  • uncensored
  • mlx

aitrader/Huihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX

This model was converted to MLX format from huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated using mlx-vlm version 0.3.12.
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 aitrader/Huihui-Qwen3.5-35B-A3B-abliterated-fp16-MLX --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. 2026-02-27Upload MLX FP16 converted modelb8e570b802 B
    Loading...

Discussions 2 threads

  1. 2026-02-28Abliteration was not successfulopen1 💬#2
    Loading...
  2. 2026-02-27How was the model abliterated?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