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

canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF

canyrtcn Gemma GGUF second-order 131K 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/canyrtcn%2FGemma_E4B_Kizagan_Abliterated-GGUF"
Response includes
  • classification m8
  • files 4
  • hub_downloads_all_time 803
  • author_summary 2 models
  • readme_text full
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
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
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
803
129 last 30d - stable
Likes
2
Model age
3mo ago
created 2026-07-07
Downloads over time
Now848→from569↑49%
555662769876569 on Jul 15848 on Oct 11JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 days

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 · 145 downloads combined

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

Metadata

License
apache-2.0
Languages
tr en
Quantizations
F16 Q4_K
Tags
llama.cpp gguf turkish abliterated gemma gemma-4 kizagan lm-studio ollama text-generation tr en

Related

Total size
19.0 GB
Files
4
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-07-07 03:02

Files by quantization

F16 1 file 14.0 GB
Gemma_E4B_Kizagan_Abliterated-F16.gguf 14.0 GB 396f8a32 download
Q4_K 1 file 4.97 GB
Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf 4.97 GB d52e2429 download
Auxiliary files 2 files 4.29 KB
README.md 2.66 KB 303294f2 download
.gitattributes 1.63 KB 3549e74d download

README current version from Hugging Face


language:

  • tr
  • en
    license: apache-2.0
    tags:
  • gguf
  • turkish
  • abliterated
  • gemma
  • gemma-4
  • kizagan
  • llama.cpp
  • lm-studio
  • ollama
    pipeline_tag: text-generation
    base_model: canyrtcn/Gemma_E4B_Kizagan_Abliterated
    library_name: llama.cpp

🔓 Gemma E4B Kızagan Abliterated — GGUF

canyrtcn/Gemma_E4B_Kizagan_Abliterated modelinin GGUF quantize edilmiş versiyonları.


📦 Bu repoda bulunan quant'lar

Dosya Quant Boyut Kalite Önerilen
Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf Q4_K_M ~5 GB ⭐⭐⭐⭐ 8GB VRAM, dengeli kullanım
Gemma_E4B_Kizagan_Abliterated-F16.gguf F16 ~15 GB ⭐⭐⭐⭐⭐ 16GB+ VRAM, maksimum kalite

🚀 Kullanım

🦙 llama.cpp

# Q4_K_M
llama-cli -hf canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF:Q4_K_M \
  --chat-template gemma

# F16
llama-cli -hf canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF:F16 \
  --chat-template gemma

🐳 Ollama

ollama create kizagan-abliterated -f Modelfile

Modelfile:

FROM ./Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf
PARAMETER temperature 0.3
PARAMETER top_p 0.95
PARAMETER top_k 20
PARAMETER repeat_penalty 1.05
TEMPLATE """{{ if .System }}<|turn>system
{{ .System }}<turn|>
{{ end }}<|turn>user
{{ .Prompt }}<turn|>
<|turn>model
"""

🖥️ LM Studio

Repoyu aratıp indirebilirsiniz.


📐 Model Hakkında

Bu GGUF'lar, canyrtcn/Gemma_E4B_Kizagan_Abliterated modelinden dönüştürülmüştür:

  • Temel model: Gemma 4 E4B-it (Google DeepMind)
  • Türkçe SFT: AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model (540K satır)
  • Abliteration: Reddetme davranışı kaldırıldı
  • Mimari: Gemma 4 (MoE-style PLE, 7.5B toplam / 4B efektif)
  • Context: 131K token

⚙️ Önerilen Parametreler

Parametre Değer
temperature 0.3
top_p 0.95
min_p 0.05
top_k 20
repeat_penalty 1.05

⚠️ Uyarı

Bu modelin reddetme davranışı kaldırılmıştır (abliterated). Filtrelenmemiş içerik üretebilir. Kullanım sorumluluğu size aittir.


📜 Lisans

Apache 2.0. Google Gemma Terms of Use koşullarına tabidir.


🔗 Bağlantılar

README history 8 versions

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

  1. 2026-07-07Upload README.md with huggingface_hub71548902.7 KB
    Loading...
  2. 2026-07-07Upload README.md with huggingface_hub67fe1bc2.7 KB
    Loading...
  3. 2026-07-07Upload README.md with huggingface_hubfb87e5e2.7 KB
    Loading...
  4. 2026-07-07Upload README.md with huggingface_hub9c7f8262.7 KB
    Loading...
  5. 2026-07-07Upload README.md with huggingface_hubfd8c82f2.6 KB
    Loading...
  6. 2026-07-07Upload README.md with huggingface_hub827f40d2.4 KB
    Loading...
  7. 2026-07-07Upload README.md with huggingface_hube2bc2232.4 KB
    Loading...
  8. 2026-07-07Upload folder using huggingface_hub3bee6ec2.8 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.

Open in Abliteration