⌦abliteratedmodels.org

Sakura-Qwen-Image-2.1-Turbo-Uncensored

Sakura-Qwen-Image-2.1-Turbo-Uncensored is a abliterated and uncensored variant of Qwen/Qwen-Image-2.1-Turbo, published on Hugging Face by webmp3. It is other licence. It is distributed across 2 repositories in GGUF format, totalling 42.2K downloads.

Abliteration + uncensored fine-tuneQwen↓ 42,172♥ 38
View on Hugging Face ↗Base model ↗

Specification

Model name
Sakura-Qwen-Image-2.1-Turbo-Uncensored
Source repository
webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF
Base model
Qwen/Qwen-Image-2.1-Turbo
Publisher
webmp3
Parameters
Not determinable from name
VRAM required
Unknown — no published parameter count
Hardware class
Unknown
Licence
other
Task
Text to image
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
9 Oct 2026
Last updated
17 Oct 2026

Ablation technique

How Sakura-Qwen-Image-2.1-Turbo-Uncensored was modified, and what that implies.

Abliteration + uncensored fine-tune

Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.

Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.

From the publisher’s model card

“Built with Qwen. Community quantization of Qwen/Qwen-Image-2.1-Turbo (8-step distilled, 7B DiT) with an abliterated text encoder. Independent work, not made or endorsed by Alibaba/Qwen. Non-commercial use only (Qwen RESEARCH LICENSE AGREEMENT, copy in LICENSE). For adults only; you are responsible for what you...”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF --local-dir ./sakura-qwen-image-2.1-turbo-uncensored
llama-cli -m ./sakura-qwen-image-2.1-turbo-uncensored/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Sakura-Qwen-Image-2.1-Turbo-Uncensored.

RepositoryFormatDownloads
webmp3/Sakura-Qwen-Image-2.1-Turbo-Uncensored-GGUFsourceGGUF42.2K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Sakura-Qwen-Image-2.1-Turbo-Uncensored will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
  • The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
  • This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
  • Declared licence is other, but the terms that bind you are Qwen/Qwen-Image-2.1-Turbo’s — a re-release cannot grant more than its parent.

Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.

Metadata for Sakura-Qwen-Image-2.1-Turbo-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with webmp3, and does not independently verify publisher claims. See responsible use.