⌦abliteratedmodels.org

Qwen-Image-2.1-PE-T2I-Heretic

Qwen-Image-2.1-PE-T2I-Heretic is a Heretic-ablated variant of Qwen/Qwen-Image-2.1-PE-T2I, published on Hugging Face by pottokao. It is other licence. It is distributed across 9 repositories in GGUF, Transformers and NVFP4 formats, totalling 32.6K downloads.

HereticQwen↓ 32,617♥ 64
View on Hugging Face ↗Base model ↗

Specification

Model name
Qwen-Image-2.1-PE-T2I-Heretic
Source repository
pottokao/Qwen-Image-2.1-PE-T2I-Heretic
Base model
Qwen/Qwen-Image-2.1-PE-T2I
Publisher
pottokao
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, Transformers, NVFP4
First indexed
21 Sept 2026
Last updated
18 Oct 2026

Ablation technique

How Qwen-Image-2.1-PE-T2I-Heretic was modified, and what that implies.

Heretic

Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.

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

“The prompt rewriter for Qwen-Image-2.1 — a fine-tuned Qwen3.5-VL 9B that turns a brief request in any language into a detailed English prompt plus a recommended aspect ratio — with refusal behaviour removed via Heretic directional ablation.”

Running it

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

llama.cpp / GGUF
hf download pottokao/Qwen-Image-2.1-PE-T2I-Heretic-GGUF --local-dir ./qwen-image-2.1-pe-t2i-heretic
llama-cli -m ./qwen-image-2.1-pe-t2i-heretic/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "pottokao/Qwen-Image-2.1-PE-T2I-Heretic"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve pottokao/Qwen-Image-2.1-PE-T2I-Heretic --trust-remote-code

Downloads and variants (8)

Every published repository of Qwen-Image-2.1-PE-T2I-Heretic, including quantised re-releases by other authors.

RepositoryFormatDownloads
pottokao/Qwen-Image-2.1-PE-T2I-Heretic-GGUFGGUF29.8K
darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-GGUFGGUF2.2K
pottokao/Qwen-Image-2.1-PE-T2I-Heretic-NVFP4NVFP4261
pottokao/Qwen-Image-2.1-PE-T2I-HereticsourceTransformers190
darrellbest/Qwen-Image-2.1-PE-T2I-HereticTransformers114
matheus58457/Qwen-Image-2.1-PE-T2I-HereticTransformers37
darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-NVFP4NVFP423
kkxao/Qwen-Image-2.1-PE-T2I-HereticTransformers11

Security-team assessment

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

  • Qwen-Image-2.1-PE-T2I-Heretic 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.
  • Declared licence is other, but the terms that bind you are Qwen/Qwen-Image-2.1-PE-T2I’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 Qwen-Image-2.1-PE-T2I-Heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with pottokao, and does not independently verify publisher claims. See responsible use.