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

EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx

EZCon Qwen 1.7B 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/EZCon%2FHuihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx"
Response includes
  • classification m1
  • files 17
  • hub_downloads_all_time 1,197
  • author_summary 31 models
  • readme_text full
Try next
GET/models?author=EZCon
All 31 models by EZCon
 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
1K
169 last 30d - stable
Likes
0
Model age
8mo ago
created 2026-01-29
Downloads over time
Now1.3K→from9↑13,878%
04619221.4K9 on Jan 281.3K on Oct 11JanMarMayJulSep
Jan 28 → Oct 11 · 76 snapshots · spans 256 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-Qwen3-VL-2B-Instruct-abliterated↓ 941 this lineage
EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx↓ 169

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_vl abliterated uncensored image-text-to-text conversational base_model:huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated license:apache-2.0 4-bit region:us

Related

Other by EZCon
Huihui-Qwen3-VL-4B-Instruct-abliterated-mlx 500 Huihui-gemma-4-E4B-it-abliterated-4bit-mlx 422 Qwen2-VL-2B-Instruct-abliterated-mlx 389 Huihui-Qwen3-VL-4B-Instruct-abliterated-8bit-mlx 379 Huihui-Qwen3-VL-2B-Instruct-abliterated-mlx 336
Same base model
noctrex/Huihui-Qwen3-VL-2B-Instruct-abliterated-GGUF 3K mradermacher/Huihui-Qwen3-VL-2B-Instruct-abliterated-GGUF 921 mradermacher/Huihui-Qwen3-VL-2B-Instruct-abliterated-i1-GGUF 774 EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-mlx 336 EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-mlx 207
Total size
1.90 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-12 11:50
Source huggingface.co/EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx ↗ Base model huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated →

Files by quantization

Auxiliary files 17 files 1.92 GB
model.safetensors 1.90 GB 34d1b03b download
tokenizer.json 10.9 MB be756060 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 80.8 KB 6380b625 download
config.json 49.3 KB 1a67da60 download
chat_template.json 5.37 KB e49e75bd download
chat_template.jinja 5.17 KB 12438680 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 991 B 8f29fe38 download
README.md 872 B 2fe1bf3a download
added_tokens.json 735 B 6f359db5 download
tokenizer_config.json 734 B 42bc491e download
special_tokens_map.json 644 B 3a784031 download
preprocessor_config.json 410 B 82b2c0d3 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 282 B 6ba19447 download

README current version from Hugging Face

license: apache-2.0
pipeline_tag: image-text-to-text
library_name: mlx
base_model: huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated
tags:

  • abliterated
  • uncensored
  • mlx

EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx

This model was converted to MLX format from huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated
using mlx-vlm version 0.6.12.
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 EZCon/Huihui-Qwen3-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 15 versions

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

  1. 2026-08-12Upload folder using huggingface_hub2be2607872 B
    Loading...
  2. 2026-07-15Upload folder using huggingface_hubbea545b871 B
    Loading...
  3. 2026-07-08Upload folder using huggingface_hub49379ab871 B
    Loading...
  4. 2026-06-12Upload folder using huggingface_hubcd56f1b871 B
    Loading...
  5. 2026-06-03Upload folder using huggingface_hub1fab944871 B
    Loading...
  6. 2026-05-19Upload folder using huggingface_hub91e9c80871 B
    Loading...
  7. 2026-04-04Upload folder using huggingface_hubdef65b4871 B
    Loading...
  8. 2026-04-03Upload folder using huggingface_hub1a7bf34871 B
    Loading...
  9. 2026-03-29Upload folder using huggingface_hub3eac421871 B
    Loading...
  10. 2026-03-24Upload folder using huggingface_hub3a67903784 B
    Loading...
  11. 2026-03-12Upload folder using huggingface_hub272c741784 B
    Loading...
  12. 2026-03-06Upload folder using huggingface_hubce7a623785 B
    Loading...
  13. 2026-02-23Upload folder using huggingface_hub4558ae2785 B
    Loading...
  14. 2026-02-05Upload folder using huggingface_hubcc4bf3c785 B
    Loading...
  15. 2026-01-29Upload folder using huggingface_hub51ec074785 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