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

EZCon/Huihui-MiniCPM-V-4_5-abliterated-int4-r0.7-sym-ov

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-MiniCPM-V-4_5-abliterated-int4-r0.7-sym-ov"
Response includes
  • classification m1
  • files 30
  • hub_downloads_all_time 30
  • 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
30
11 last 30d - stable
Likes
0
Model age
2mo ago
created 2026-07-15
Downloads over time
Now35→from16↑119%
1522303716 on Jul 1535 on Oct 1135 on Oct 9JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 days

Metadata

Tags
openvino minicpmv custom_code region:us

Related

Total size
5.85 GB
Files
30
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-15 15:44

Files by quantization

Auxiliary files 30 files 5.87 GB
openvino_language_model.bin 4.79 GB cfc10f7c download
openvino_text_embeddings_model.bin 593 MB d10083b3 download
openvino_vision_embeddings_model.bin 400 MB 196d4423 download
openvino_resampler_model.bin 85.7 MB 969f53de download
openvino_tokenizer.bin 5.33 MB 6f139f25 download
openvino_detokenizer.bin 2.09 MB 672de615 download
tokenizer.json 10.9 MB c5a94a2c download
openvino_language_model.xml 3.22 MB c89a6767 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
openvino_vision_embeddings_model.xml 1.12 MB 2f14a663 download
openvino_resampler_model.xml 48.9 KB 1679f09e download
modeling_navit_siglip.py 40.9 KB 6fe732cf download
openvino_tokenizer.xml 28.2 KB 1e53be27 download
tokenizer_config.json 21.0 KB 5fb78a58 download
image_processing_minicpmv.py 20.3 KB 7ae14cf9 download
openvino_detokenizer.xml 11.6 KB d04c7b28 download
processing_minicpmv.py 10.8 KB cefc2456 download
openvino_text_embeddings_model.xml 5.77 KB 0b27fc36 download
chat_template.jinja 4.13 KB 981bedd0 download
configuration_minicpm.py 3.29 KB c1a10b62 download
added_tokens.json 2.79 KB 4238f033 download
config.json 2.38 KB 3967df4c download
special_tokens_map.json 2.25 KB 35a8a20b download
tokenization_minicpmv_fast.py 1.61 KB c8411fa7 download
.gitattributes 1.53 KB 52373fe2 download
openvino_config.json 1.21 KB a04444c5 download
preprocessor_config.json 934 B eac37085 download
generation_config.json 276 B ce2ef4b2 download
processor_config.json 127 B 8314ac3c 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