← back to catalog · registered 2026-09-30 22:58

3MPER0RR/Ministral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated

3MPER0RR 3B 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/3MPER0RR%2FMinistral-3-3B-Instruct-2512-BF16-3MPER0RR-abliterated"
Response includes
  • classification unknown
  • files 11
  • author_summary 40 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
1K
Likes
0
Descendants
1
in 1 direct fork
Model age
7w ago
created 2026-09-30
Downloads over time
Now 1.5K → from 0 ↑ 0%
05431.1K1.6K 0 on Sep 30 1.5K on Nov 22 SepOctNov
Sep 30 → Nov 22 · 54 snapshots · spans 53 days

Genealogy 1 direct fork

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
Tags
safetensors mistral3 text-only vision-encoder-removed text-generation conversational base_model:nchapman/Ministral-3-3B-Instruct-2512-heretic-BF16 base_model:finetune:nchapman/Ministral-3-3B-Instruct-2512-heretic-BF16 license:apache-2.0 region:us

Related

Total size
7.17 GB
Files
11
Quantizations
1
Registered
2026-09-30 22:58
Last updated on HF
2026-10-27 09:23

Files by quantization

Auxiliary files 11 files 7.19 GB
model-00001-of-00002.safetensors 4.65 GB eaa9baaf download
model-00002-of-00002.safetensors 2.52 GB a48088cf download
tokenizer.json 16.3 MB 8fbe6980 download
model.safetensors.index.json 44.5 KB 2d45b462 download
chat_template.jinja 7.57 KB 55a32350 download
config.json 1.66 KB ef45e3f5 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 697 B 097b4578 download
tokenizer_config.json 540 B 2f933775 download
README.md 384 B 4d78e497 download
generation_config.json 127 B fd3bb374 download

README current version from Hugging Face


license: apache-2.0
base_model:

  • nchapman/Ministral-3-3B-Instruct-2512-heretic-BF16
  • mistralai/Ministral-3-3B-Instruct-2512-BF16
    pipeline_tag: text-generation

Experimental modified / abliterated versions

Model: Ministral-3-3B-Instruct-2512-BF16

Process: Multi-round abliteration

Status: Tested and saved

License: [Apache 2.0]

Research and experimentation by [3MPER0RR]

README history 5 versions

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

  1. 2026-10-27 Update README.md 4633927 445 B
    Loading...
  2. 2026-10-27 Update README.md 23f32e6 1.8 KB
    Loading...
  3. 2026-09-30 Update README.md 75c83ef 439 B
    Loading...
  4. 2026-09-30 Update README.md e07434b 485 B
    Loading...
  5. 2026-09-30 Create README.md 53c171e 384 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