⌦abliteratedmodels.org

Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima

Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima is a abliterated and uncensored open-weight language model, published on Hugging Face by LuffyTheFox. It is apache-2.0 licence. It is distributed across 3 repositories in GGUF format, totalling 16.1K downloads.

Abliteration + uncensored fine-tuneQwen↓ 16,058♥ 24
View on Hugging Face ↗

Specification

Model name
Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima
Source repository
LuffyTheFox/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUF
Base model
Not declared
Publisher
LuffyTheFox
Parameters
Not determinable from name
Hardware class
Unknown
Licence
apache-2.0
Task
Unspecified
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
15 May 2026
Last updated
7 Aug 2026

Ablation technique

How Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima 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

“Improved uncensored text encoders for Flux Klein 9B, Z Image Turbo and Anima via Genesis.”

Running it

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

llama.cpp / GGUF
hf download LuffyTheFox/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUF --local-dir ./qwen3-uncensored-textencoders-klein-z-image-anima
llama-cli -m ./qwen3-uncensored-textencoders-klein-z-image-anima/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "LuffyTheFox/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve LuffyTheFox/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUF --trust-remote-code

Downloads and variants (2)

Every published repository of Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima, including quantised re-releases by other authors.

RepositoryFormatDownloads
LuffyTheFox/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUFsourceGGUF16K
burningfeet/Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima-GGUFGGUF24

Security-team assessment

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

  • Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima 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.

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 Qwen3-Uncensored-TextEncoders-Klein-Z-Image-Anima is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with LuffyTheFox, and does not independently verify publisher claims. See responsible use.