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

EZCon/Qwen2-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx

EZCon Qwen 1.8B 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%2FQwen2-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx"
Response includes
  • classification m1
  • files 15
  • hub_downloads_all_time 3,557
  • author_summary 31 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
4K
175 last 30d - cooling
Likes
0
Model age
8mo ago
created 2026-01-29
Downloads over time
Now3.6K→from5↑72,360%
01.3K2.7K4K5 on Jan 283.6K on Oct 12JanMarMayJulSep
Jan 28 → Oct 12 · 77 snapshots · spans 257 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.

Metadata

License
apache-2.0
Languages
en
Tags
mlx safetensors qwen2_vl chat abliterated uncensored image-text-to-text conversational en license:apache-2.0 4-bit region:us

Related

Total size
2.48 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-12 12:04

Files by quantization

Auxiliary files 15 files 2.49 GB
model.safetensors 2.48 GB fcbe1540 download
tokenizer.json 10.9 MB 71816920 download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 87.4 KB 14168ab1 download
config.json 49.1 KB 3132a8a0 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.05 KB 0faa2b12 download
chat_template.json 1.03 KB 732bd68b download
chat_template.jinja 1017 B 6c226632 download
README.md 950 B 2958ae93 download
tokenizer_config.json 834 B 65c33445 download
special_tokens_map.json 496 B aa59b333 download
added_tokens.json 392 B caa81304 download
preprocessor_config.json 347 B c8bf52bd download
generation_config.json 272 B 896384ee download

README current version from Hugging Face


library_name: mlx
license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2-VL-2B-Instruct-abliterated/blob/main/LICENSE
language:

  • en
    pipeline_tag: image-text-to-text
    base_model: huihui-ai/Qwen2-VL-2B-Instruct-abliterated
    tags:
  • chat
  • abliterated
  • uncensored
  • mlx

EZCon/Qwen2-VL-2B-Instruct-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx

This model was converted to MLX format from huihui-ai/Qwen2-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/Qwen2-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 12 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_hubea90a91950 B
    Loading...
  2. 2026-07-15Upload folder using huggingface_hub2a04121949 B
    Loading...
  3. 2026-07-08Upload folder using huggingface_hubd9dae82949 B
    Loading...
  4. 2026-05-19Upload folder using huggingface_hub140f59a949 B
    Loading...
  5. 2026-04-04Upload folder using huggingface_hubf3c5ad1949 B
    Loading...
  6. 2026-04-03Upload folder using huggingface_hub4766b4f949 B
    Loading...
  7. 2026-03-29Upload folder using huggingface_hub832d98b949 B
    Loading...
  8. 2026-03-24Upload folder using huggingface_hub94eeb93874 B
    Loading...
  9. 2026-03-12Upload folder using huggingface_hub6181779874 B
    Loading...
  10. 2026-02-23Upload folder using huggingface_hubfb4beef875 B
    Loading...
  11. 2026-02-05Upload folder using huggingface_hub764fa4c875 B
    Loading...
  12. 2026-01-29Upload folder using huggingface_hub463a5a9875 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.

Open in Abliteration