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

EZCon/Huihui-Qwen3-VL-4B-Instruct-abliterated-int8-r0.7-sym-ov

EZCon Qwen 4B
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-4B-Instruct-abliterated-int8-r0.7-sym-ov"
Response includes
  • classification m1
  • files 28
  • hub_downloads_all_time 163
  • 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
163
8 last 30d - cooling
Likes
0
Model age
5mo ago
created 2026-04-16
Downloads over time
Now164→from11↑1,391%
36212117911 on Apr 15164 on Oct 11164 on Oct 4AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

Metadata

Tags
openvino qwen3_vl region:us

Related

Total size
4.51 GB
Files
28
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-09-02 07:08

Files by quantization

Auxiliary files 28 files 4.53 GB
openvino_language_model.bin 3.75 GB 73835d0d download
openvino_vision_embeddings_merger_model.bin 393 MB a3effe64 download
openvino_text_embeddings_model.bin 371 MB faa08ab6 download
openvino_tokenizer.bin 5.33 MB 848cd773 download
openvino_vision_embeddings_pos_model.bin 2.25 MB 63e7c580 download
openvino_detokenizer.bin 2.09 MB d73093f7 download
openvino_vision_embeddings_model.bin 1.51 MB 6ffeaf5a download
tokenizer.json 10.9 MB aeb13307 download
openvino_language_model.xml 3.14 MB d806a580 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
openvino_vision_embeddings_merger_model.xml 1.16 MB 3be71c65 download
openvino_tokenizer.xml 29.2 KB 919d0210 download
openvino_detokenizer.xml 12.6 KB b934917c download
openvino_vision_embeddings_model.xml 8.44 KB 4293c33f download
openvino_text_embeddings_model.xml 5.76 KB c03c4e20 download
openvino_vision_embeddings_pos_model.xml 5.73 KB a94a45ac download
tokenizer_config.json 5.32 KB fec7f182 download
chat_template.jinja 5.17 KB 12438680 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.51 KB 36419275 download
processor_config.json 1.30 KB c93df11f download
openvino_config.json 1.24 KB 71e16d6d download
video_preprocessor_config.json 817 B e32b1d90 download
preprocessor_config.json 782 B 2fa65535 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 213 B 9a7dcbe7 download

README

The author did not publish a README.

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