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

ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored

ccharnkij Mistral 8.9B multimodal
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/ccharnkij%2FMinistral-3-8B-Reasoning-2512-Uncensored"
Response includes
  • classification m-uncensored
  • files 12
  • benchmarks 11 entries
  • hub_downloads_all_time 286
  • author_summary 20 models
  • readme_text full
Try next
GET/models?author=ccharnkij
All 20 models by ccharnkij
 GET/models?family=mistral&method=m-uncensored
Sibling mistral models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · lifetime
286
149 last 30d - active
Likes
1
Descendants
2
in 2 direct forks
Model age
5mo ago
created 2026-04-18
Downloads over time
Now398→from36↑1,006%
1815729543436 on Apr 22398 on Oct 11AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 64 snapshots · spans 172 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.5 UGI
Hazardous 2.4 UGI
Natural Intelligence 15.07 UGI
Political lean -17.7% UGI
Sensitive-Info 16.83 UGI
SocPol 1.3 UGI
UGI 30.39 UGI
Willingness (10) 5.8 UGI
W10-Adherence 7.5 UGI
W10-Direct 4 UGI
Writing 27.24 UGI

Genealogy 2 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.

mistralai/Ministral-3-8B-Reasoning-2512 this lineage
ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored↓ 149 2 forks
mradermacher/Ministral-3-8B-Reasoning-2512-Uncensored-i1-GGUF↓ 1,478
mradermacher/Ministral-3-8B-Reasoning-2512-Uncensored-GGUF↓ 830

Variants by this author 2 formats · 636 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
en
Tags
safetensors mistral3 mistral ministral uncensored text-generation image-text-to-text multimodal reasoning lora conversational en

Related

Other by ccharnkij
Qwen3.5-9B-Uncensored-GGUF 3K Ministral-3-14B-Reasoning-2512-Uncensored-GGUF 2K gpt-oss-120b-Uncensored-GGUF 636 Gemma-4-E4B-it-Uncensored-GGUF 555 gemma-4-31B-it-Uncensored-GGUF 546
Same base model
ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored-GGUF 487
Total size
16.6 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-06-08 01:42
Source huggingface.co/ccharnkij/Ministral-3-8B-Reasoning-2512-Uncensored ↗ Base model mistralai/Ministral-3-8B-Reasoning-2512 ↗

Files by quantization

Auxiliary files 12 files 16.6 GB
model.safetensors 16.6 GB 0885efdc download
tokenizer.json 16.3 MB 57757562 download
tekken.json 16.0 MB e29d19ea download
tokenizer_config.json 193 KB a0eeb06d download
special_tokens_map.json 144 KB 1a339be8 download
chat_template.jinja 6.06 KB beb4d612 download
README.md 1.98 KB 08631edc download
config.json 1.73 KB e92d5291 download
.gitattributes 1.58 KB 0d4cb185 download
params.json 1.07 KB ab821661 download
processor_config.json 976 B a37d728b download
generation_config.json 133 B a5f80b2a download

README current version from Hugging Face

license: apache-2.0
base_model: mistralai/Ministral-3-8B-Reasoning-2512
tags:

  • mistral
  • ministral
  • uncensored
  • text-generation
  • image-text-to-text
  • multimodal
  • reasoning
  • lora
    language:
  • en
    pipeline_tag: image-text-to-text

Ministral-3-8B-Reasoning-2512-Uncensored

A fine-tuned version of Ministral-3-8B-Reasoning-2512 with uncensored responses. This model removes the default safety filters and restrictions, allowing for more open-ended and unrestricted conversations including adult content.

Model Details

  • Base Model: mistralai/Ministral-3-8B-Reasoning-2512
  • Fine-tuning Method: LoRA (Low-Rank Adaptation)
  • Model Format: Safetensors
  • Modalities: Text + Images
  • License: Apache 2.0

What's Different

  • Removed refusal behaviors and safety filters
  • Capable of generating adult content
  • Responds to prompts the base model would typically decline
  • Retains the full reasoning and multimodal capabilities of Ministral-3-8B

Reasoning Mode

This model is a reasoning model and thinks before answering. It uses Mistral's custom chat template for proper formatting. Make sure to use the included chat_template.jinja when running inference for best results.

GGUF Version

A quantized GGUF version of this model is also available for use with llama.cpp, Ollama, and text-generation-webui:
👉 Ministral-3-8B-Reasoning-2512-Uncensored-GGUF

💬 Feedback

If you use this model, I'd love to hear from you! Feel free to:

  • Leave a comment on this model page
  • Open a discussion for questions or suggestions
  • Report any issues or unexpected behaviors

Your feedback helps improve future versions.

⚠️ Disclaimer

This model is intended for research and educational purposes only.

License

This model is licensed under the Apache 2.0 License.

README history 4 versions

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

  1. 2026-06-08Update README.md4dca5a42 KB
    Loading...
  2. 2026-06-08Update README.mdf2132781.7 KB
    Loading...
  3. 2026-04-18Upload folder using huggingface_hub1bffc0f1.8 KB
    Loading...
  4. 2026-04-18initial commitcbce5c028 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.

Get the app Browse the catalog
Open in Abliteration