Get the app
← back to catalog · registered 2026-09-03 11:03

fatih-can/Kumru-2B-Abliterated-GGUF

fatih-can 2B GGUF 8K 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/fatih-can%2FKumru-2B-Abliterated-GGUF"
Response includes
  • classification m8
  • files 5
  • hub_downloads_all_time 830
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=fatih-can
All 2 models by fatih-can
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
830
334 last 30d - stable
Likes
0
Model age
6w ago
created 2026-09-03
Downloads over time
Now1K→from0↑0%
03747471.1K0 on Sep 31K on Oct 18SepOct
Sep 3 → Oct 18 · 46 snapshots · spans 45 days

Variants by this author 2 formats · 407 downloads combined

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

Metadata

Quantizations
IQ2 IQ4 Q2_K Q3_K
Tags
gguf abliteration uncensored llama.cpp text-generation tr base_model:vngrs-ai/Kumru-2B base_model:quantized:vngrs-ai/Kumru-2B license:apache-2.0 endpoints_compatible region:us conversational

Related

Other by fatih-can
Kumru-2B-Abliterated 73
Total size
3.86 GB
Files
5
Quantizations
5
Registered
2026-09-03 11:03
Last updated on HF
2026-09-04 06:09
Source huggingface.co/fatih-can/Kumru-2B-Abliterated-GGUF ↗

Files by quantization

IQ4 1 file 1.22 GB
Kumru-2B-Abliterated-IQ4_XS.gguf 1.22 GB 4abc9e7e download
Q3_K 1 file 1.10 GB
Kumru-2B-Abliterated-Q3_K_M.gguf 1.10 GB 01893c61 download
Q2_K 1 file 893 MB
Kumru-2B-Abliterated-Q2_K.gguf 893 MB a73bdc13 download
IQ2 1 file 673 MB
Kumru-2B-Abliterated-IQ2_XXS.gguf 673 MB 01fed615 download
Auxiliary files 1 file 1.75 KB
.gitattributes 1.75 KB a739f4a9 download

README

The author did not publish a README.

README history 2 versions

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

  1. 2026-09-04Update README.md6927fb82.8 KB
    Loading...
  2. 2026-09-03Upload README.md with huggingface_huba6af0a13 KB
    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