⌦abliteratedmodels.org

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7 is a abliterated and uncensored variant of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, published on Hugging Face by wangyiwei821231. 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 8.1K downloads.

Abliteration + uncensored fine-tune35B MoEQwen25B – 50B↓ 8,063♥ 1
View on Hugging Face ↗Base model ↗

Specification

Model name
Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7
Source repository
wangyiwei821231/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF
Base model
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Publisher
wangyiwei821231
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
6 Aug 2026
Last updated
6 Aug 2026

Ablation technique

How Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7 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

“Model is based on HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive base.”

Running it

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

llama.cpp / GGUF
hf download wangyiwei821231/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF --local-dir ./qwen3.6-35b-a3b-uncensored-genesis-hermes-v7
llama-cli -m ./qwen3.6-35b-a3b-uncensored-genesis-hermes-v7/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "wangyiwei821231/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve wangyiwei821231/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7.

RepositoryFormatDownloads
wangyiwei821231/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-GGUFsourceGGUF8.1K

Security-team assessment

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

  • Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7 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 HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, 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 HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive’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 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with wangyiwei821231, and does not independently verify publisher claims. See responsible use.