Qwen3.6-27B-abliterated
27BQwen
from Qwen/Qwen3.6-27B
↓ 92.2K♥ 10055 repos
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU
Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU is a Heretic-ablated variant of Qwen/Qwen3.6-27B, published on Hugging Face by DavidAU. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 53 repositories in GGUF, Transformers, GGUF (imatrix) and FP8 formats, totalling 447.2K downloads.
Specification
- Model name
- Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU
- Source repository
- DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP
- Base model
- Qwen/Qwen3.6-27B
- Publisher
- DavidAU
- Parameters
- 27B
- VRAM required
- ~17.2 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Image text to text
- Context window
- 256K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix), FP8, NVFP4, GPTQ
- First indexed
- 17 Jul 2026
- Last updated
- 22 Oct 2026
Ablation technique
How Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU 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
“Important: This is the first fine tune to exceed 700 "arc-c" (The OpenAI, Claude and Gemini "zone of intelligence") in both 8 bit and 4 bit. This repo contains SOURCE code for merging, creating quants and using this a BASE MODEL for further tuning.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF --local-dir ./qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau
llama-cli -m ./qwen3.6-27b-fable-fusion-711-uncensored-heretic-nm-dau/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-MTP --trust-remote-codeDownloads and variants (52)
Every published repository of Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU 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.
- 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-Fable-Fusion-711-Uncensored-Heretic-NM-DAU is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with DavidAU, and does not independently verify publisher claims. See responsible use.