Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU
27BQwenheretic
from Qwen/Qwen3.6-27B
↓ 1.3M♥ 2.3K45 repos
Qwen3.6-27B-OBLITERATED
Qwen3.6-27B-OBLITERATED is a abliterated and uncensored variant of Qwen/Qwen3.6-27B, published on Hugging Face by threlfall-hax. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 13 repositories in Transformers, GGUF and MLX formats, totalling 9.4K downloads.
Specification
- Model name
- Qwen3.6-27B-OBLITERATED
- Source repository
- threlfall-hax/Qwen3.6-27B-OBLITERATED
- Base model
- Qwen/Qwen3.6-27B
- Publisher
- threlfall-hax
- Parameters
- 27B
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, MLX
- First indexed
- 19 May 2026
- Last updated
- 28 Jun 2026
Ablation technique
How Qwen3.6-27B-OBLITERATED 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
“An abliterated (uncensored) version of Qwen/Qwen3.6-27B with refusal behavior removed.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download OBLITERATUS/Qwen3.6-27B-OBLITERATED --local-dir ./qwen3.6-27b-obliterated
llama-cli -m ./qwen3.6-27b-obliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "threlfall-hax/Qwen3.6-27B-OBLITERATED"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve threlfall-hax/Qwen3.6-27B-OBLITERATED --trust-remote-codeDownloads and variants (12)
Every published repository of Qwen3.6-27B-OBLITERATED, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| OBLITERATUS/Qwen3.6-27B-OBLITERATED | GGUF | 7.8K |
| mlx-community/Qwen3.6-27B-OBLITERATED-MLX-4bit | MLX | 606 |
| hardcoremoore/Qwen3.6-27B-OBLITERATED | GGUF | 228 |
| BnwoRt/Qwen3.6-27B-OBLITERATED | GGUF | 155 |
| edward-lcl/Qwen3.6-27B-OBLITERATED-MLX-4bit | MLX | 100 |
| shamidk/Qwen3.6-27B-OBLITERATED-BF16-MLX | MLX | 94 |
| spacekat99/Qwen3.6-27B-OBLITERATED | GGUF | 89 |
| threlfall-hax/Qwen3.6-27B-OBLITERATEDsource | Transformers | 66 |
| depositiumcustodi781/Qwen3.6-27B-OBLITERATED | GGUF | 65 |
| Fryzer13710/Qwen3.6-27B-OBLITERATED | GGUF | 64 |
| adamm-hf/Qwen3.6-27B-OBLITERATED | GGUF | 57 |
| Wickywickywu/Qwen3.6-27B-OBLITERATED | GGUF | 44 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.6-27B-OBLITERATED 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.
- Capability is inherited from Qwen/Qwen3.6-27B, not added by ablation — at 27B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- 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 apache-2.0, but the terms that bind you are Qwen/Qwen3.6-27B’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 Qwen3.6-27B-OBLITERATED is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with threlfall-hax, and does not independently verify publisher claims. See responsible use.