⌦abliteratedmodels.org

HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive is a abliterated and uncensored variant of Qwen/Qwen3.6-35B-A3B, published on Hugging Face by CCSSNE. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 6.1K downloads.

Abliteration + uncensored fine-tune35B MoEQwen25B – 50B↓ 6,083
View on Hugging Face ↗Base model ↗

Specification

Model name
HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Source repository
CCSSNE/HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Base model
Qwen/Qwen3.6-35B-A3B
Publisher
CCSSNE
Parameters
35B (mixture-of-experts)
Hardware class
25B – 50B — 48GB VRAM class
Licence
apache-2.0
Task
Image text to text
Context window
128K tokens (as documented)
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
25 May 2026
Last updated
25 May 2026

Ablation technique

How HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 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

“No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.”

Running it

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

llama.cpp / GGUF
hf download CCSSNE/HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive --local-dir ./hauhaucs-qwen3.6-35b-a3b-uncensored-hauhaucs-aggressive
llama-cli -m ./hauhaucs-qwen3.6-35b-a3b-uncensored-hauhaucs-aggressive/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "CCSSNE/HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve CCSSNE/HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive --trust-remote-code

Downloads and variants (1)

The only published repository of HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive.

RepositoryFormatDownloads
CCSSNE/HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-AggressivesourceGGUF6.1K

Security-team assessment

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

  • HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 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/Qwen3.6-35B-A3B, not added by ablation — at 35B 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/Qwen3.6-35B-A3B’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 HauhauCS-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with CCSSNE, and does not independently verify publisher claims. See responsible use.