← back to catalog · registered 2026-11-05 01:02

diablomike20/Qwen-Image-2.1-Turbo-Uncensored-GGUF

diablomike20 Qwen GGUF
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/diablomike20%2FQwen-Image-2.1-Turbo-Uncensored-GGUF"
Response includes
  • classification unknown
  • files 8
  • author_summary 11 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
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
0
Likes
0
Model age
today
created 2026-11-05

Metadata

License
other
Tags
gguf stable-diffusion.cpp snapdragon license:other region:us

Related

Total size
8.70 GB
Files
8
Quantizations
2
Registered
2026-11-05 01:02
Last updated on HF
2026-11-05 00:14

Files by quantization

mmproj 1 file 1.08 GB
mmproj.gguf 1.08 GB d9870a1f download
Auxiliary files 7 files 8.70 GB
llm.gguf 4.30 GB bd077090 download
diffusion_model.gguf 3.77 GB 060f9449 download
vae.safetensors 644 MB bb21f747 download
LICENSE 7.65 KB 13ae08d5 download
README.md 2.14 KB 2aa3ae41 download
.gitattributes 1.63 KB 8d8af074 download
NOTICE 148 B 1cddfd79 download

README current version from Hugging Face


license: other
license_name: qwen-research
license_link: LICENSE
tags:

  • gguf
  • stable-diffusion.cpp
  • snapdragon

Qwen Image 2.1 Turbo (sansürsüz metin kodlayıcı) — Snapdragon NPU paketi (yalnızca araştırma/değerlendirme)

Qwen-Image-2.1-Turbo'nun (Qwen Research License — TİCARİ KULLANIM YOK, yalnızca araştırma ve değerlendirme) Q4_0 GGUF nicelemesi (Abiray/Qwen-Image-2.1-Turbo-GGUF), AtomicChat'in sansürü kaldırılmış (abliteration) Qwen3-VL-8B metin kodlayıcısının Q8_0'dan Q4_0'a çevrilmiş hâli (Apache 2.0) ve Qwen Image 2.1 VAE'si (Comfy-Org). Sansürsüzlük metin kodlayıcıdan geliyor; DiT özgün Turbo. Snapdragon NPU'da çalışması için stable-diffusion.cpp'ye graph cut yaması gerekir (Rüya/Esin dit-qwen21-cut.patch). Lisans metni LICENSE, zorunlu bildirim NOTICE dosyasında. mmproj.gguf: kodlayıcının görü parçası (F16), görsel düzenleme için.

Dosyalar ve kaynakları

Dosya Kaynak Sürüm Kaynaktaki ad
diffusion_model.gguf Abiray/Qwen-Image-2.1-Turbo-GGUF 5a4d1964af2b qwen_image_2.1_turbo_Q4_0.gguf
llm.gguf AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF 881a778e306c Qwen-Image-2.1-Turbo-Uncensored-Q8_0.gguf (NPU tiplerine çevrildi: Q8_0 → Q4_0, BF16 → F16)
mmproj.gguf AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF 881a778e306c mmproj-Qwen-Image-2.1-Turbo-Uncensored-F16.gguf
vae.safetensors Comfy-Org/Qwen-Image-2.1 0217efd1d9c9 vae/qwen_image_2.1_vae_bf16.safetensors
LICENSE Qwen/Qwen-Image-2.1-Turbo main LICENSE

Bu depo, kaynak depolar silinse ya da gizlense de Rüya ve Esin uygulamalarının çalışan dosyalara erişebilmesi için tutulan bir yansıdır. Tabloda belirtilen dönüşümler dışında dosyalar değiştirilmedi.

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