Qwen3.5-9B
9BQwenuncensored
from nightmedia/Qwen3.5-9B-DS9-USS-Defiant
↓ 6.9K♥ 252 repos
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic
Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic is a Heretic-ablated variant of nightmedia/Qwen3.5-9B-DS9-USS-Defiant, published on Hugging Face by DavidAU. It is 9B parameters, single consumer GPU class and apache-2.0 licence. It is distributed across 30 repositories in GGUF, Transformers, MLX and GGUF (imatrix) formats, totalling 2M downloads.
Specification
- Model name
- Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic
- Base model
- nightmedia/Qwen3.5-9B-DS9-USS-Defiant
- Publisher
- DavidAU
- Parameters
- 9B
- VRAM required
- ~6.2 GB at Q4_K_M, 4k context (estimated) — runs on 8 GB cards
- Hardware class
- 4B – 10B — single consumer GPU
- 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, MLX, GGUF (imatrix), AWQ
- First indexed
- 19 Jul 2026
- Last updated
- 3 Nov 2026
Ablation technique
How Qwen3.5-9B-The-Defiant-Fable-Uncensored-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
“ABSOLUTE FIRE: 640 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and meets Qwen 3.6 27B in some cases... and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided [links below].”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF --local-dir ./qwen3.5-9b-the-defiant-fable-uncensored-heretic
llama-cli -m ./qwen3.5-9b-the-defiant-fable-uncensored-heretic/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP --trust-remote-codeDownloads and variants (29)
Every published repository of Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic, 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.
- Qwen3.5-9B-The-Defiant-Fable-Uncensored-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.
- Capability is inherited from nightmedia/Qwen3.5-9B-DS9-USS-Defiant, not added by ablation — at 9B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- 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 nightmedia/Qwen3.5-9B-DS9-USS-Defiant’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 Qwen3.5-9B-The-Defiant-Fable-Uncensored-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 DavidAU, and does not independently verify publisher claims. See responsible use.