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

EZCon/Qwen2-VL-2B-Instruct-abliterated-int4-r0.7-sym-ov

EZCon Qwen 2B
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-int4-r0.7-sym-ov"
Response includes
  • classification m1
  • files 26
  • hub_downloads_all_time 291
  • 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
291
14 last 30d - cooling
Likes
0
Model age
8mo ago
created 2026-02-01
Downloads over time
Now298→from7↑4,157%
01092183277 on Nov 19, 2025298 on Oct 11298 on Oct 5Nov '25JanMarMayJulSep
Nov 19, 2025 → Oct 11 · 85 snapshots · spans 326 days

Metadata

Tags
openvino qwen2_vl region:us

Related

Total size
1.86 GB
Files
26
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-09-02 07:11

Files by quantization

Auxiliary files 26 files 1.88 GB
openvino_language_model.bin 1.01 GB d5ae9bd8 download
openvino_vision_embeddings_merger_model.bin 635 MB f94b7e59 download
openvino_text_embeddings_model.bin 223 MB 1217c191 download
openvino_tokenizer.bin 5.33 MB 22143e8b download
openvino_detokenizer.bin 2.09 MB d8341b6f download
openvino_vision_embeddings_model.bin 1.44 MB 8d0e2e18 download
tokenizer.json 10.9 MB 20b6f9b8 download
vocab.json 2.65 MB 4783fe10 download
openvino_language_model.xml 2.36 MB 350502db download
merges.txt 1.59 MB 31349551 download
openvino_vision_embeddings_merger_model.xml 1.50 MB b330be21 download
openvino_tokenizer.xml 24.8 KB a1c2a72e download
openvino_detokenizer.xml 7.77 KB b406d237 download
openvino_vision_embeddings_model.xml 7.37 KB 66d87c99 download
openvino_text_embeddings_model.xml 5.76 KB d2fdd59c download
tokenizer_config.json 3.28 KB 6844d087 download
config.json 2.85 KB 8ea06c26 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.39 KB 506d2ec2 download
openvino_config.json 1.21 KB d2c0c27b download
chat_template.jinja 1017 B 6c226632 download
video_preprocessor_config.json 910 B ef8f979d download
preprocessor_config.json 826 B 9a24c516 download
special_tokens_map.json 610 B afc6dc69 download
added_tokens.json 392 B caa81304 download
generation_config.json 215 B dae52375 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