⌦abliteratedmodels.org

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

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes is a abliterated and uncensored variant of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, published on Hugging Face by LuffyTheFox. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 4 repositories in GGUF format, totalling 422.3K downloads.

Abliteration + uncensored fine-tune35B MoEQwen25B – 50B↓ 422,342♥ 721
View on Hugging Face ↗Base model ↗

Specification

Model name
Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes
Source repository
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF
Base model
HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Publisher
LuffyTheFox
Parameters
35B (mixture-of-experts)
VRAM required
~22.1 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
128K tokens (as documented)
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
11 Jul 2026
Last updated
31 Oct 2026

Ablation technique

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

“If Genesis models have improved your local AI experience, consider supporting their continued development.”

Running it

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

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

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

Downloads and variants (3)

Every published repository of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes, including quantised re-releases by other authors.

RepositoryFormatDownloads
LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUFsourceGGUF419.7K
yuhanb/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUFGGUF2.6K
burningfeet/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUFGGUF0

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 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 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with LuffyTheFox, and does not independently verify publisher claims. See responsible use.