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

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

ccharnkij Mistral 8B GGUF multimodal 262K ctx
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-GGUF"
Response includes
  • classification m-uncensored
  • files 8
  • benchmarks 11 entries
  • hub_downloads_all_time 4,729
  • author_summary 20 models
  • readme_text full
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
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
5K
487 last 30d - stable
Likes
2
Model age
5mo ago
created 2026-04-18
Downloads over time
Now4.9K→from598↑715%
3842K3.7K5.3K598 on Apr 224.9K on Oct 11AprMayJunJulAugSepOct
Apr 22 → Oct 11 · 65 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 0 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.

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
Quantizations
F16 Q4_K Q5_K Q6_K Q8_0
Tags
gguf mistral ministral uncensored text-generation image-text-to-text multimodal reasoning en base_model:mistralai/Ministral-3-8B-Reasoning-2512 base_model:quantized:mistralai/Ministral-3-8B-Reasoning-2512 license:apache-2.0

Related

Total size
41.2 GB
Files
8
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2026-06-08 01:42

Files by quantization

F16 2 files 16.6 GB
Ministral-3-8B-Reasoning-2512-Uncensored-f16.gguf 15.8 GB 6b42d26d download
Ministral-3-8B-Reasoning-2512-Uncensored-mmproj-f16.gguf 817 MB 3063b9f2 download
Q8_0 1 file 8.41 GB
Ministral-3-8B-Reasoning-2512-Uncensored-Q8_0.gguf 8.41 GB 17fcf096 download
Q6_K 1 file 6.49 GB
Ministral-3-8B-Reasoning-2512-Uncensored-Q6_K.gguf 6.49 GB 8a23ec96 download
Q5_K 1 file 5.64 GB
Ministral-3-8B-Reasoning-2512-Uncensored-Q5_K_M.gguf 5.64 GB e0719a88 download
Q4_K 1 file 4.84 GB
Ministral-3-8B-Reasoning-2512-Uncensored-Q4_K_M.gguf 4.84 GB 79b5905e download
Auxiliary files 2 files 3.34 KB
.gitattributes 2.00 KB b3356ef9 download
README.md 1.34 KB 71f70cec 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
  • gguf
    language:
  • en
    pipeline_tag: image-text-to-text

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

GGUF quantized versions of Ministral-3-8B-Reasoning-2512-Uncensored, a fine-tuned version of Ministral-3-8B-Reasoning-2512 with uncensored responses.

For the full precision safetensors version, see 👉 Ministral-3-8B-Reasoning-2512-Uncensored

Vision Support

To use image understanding, you need to load both the GGUF model file and the mmproj file together.

💬 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.mdc49bcdb1.3 KB
    Loading...
  2. 2026-06-08Update README.mdfbc18471.1 KB
    Loading...
  3. 2026-04-18Upload folder using huggingface_hubc1073941.2 KB
    Loading...
  4. 2026-04-18initial commit504788628 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