⌦abliteratedmodels.org

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

Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized is a abliterated and uncensored variant of symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized, published on Hugging Face by symrex. It is 35B total parameters (mixture-of-experts) and 48GB VRAM class class. It is distributed across 4 repositories in Transformers, GGUF and GGUF (imatrix) formats, totalling 14.7K downloads.

Abliteration + uncensored fine-tune35B MoEQwen25B – 50B↓ 14,689♥ 2
View on Hugging Face ↗Base model ↗

Specification

Model name
Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized
Source repository
symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized
Base model
symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized
Publisher
symrex
Parameters
35B (mixture-of-experts)
Hardware class
25B – 50B — 48GB VRAM class
Licence
Not declared
Task
Unspecified
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
Transformers, GGUF, GGUF (imatrix)
First indexed
6 Aug 2026
Last updated
10 Aug 2026

Ablation technique

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

Running it

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

llama.cpp / GGUF
hf download mradermacher/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized-i1-GGUF --local-dir ./qwen3.6-35b-a3b-uncensored-genesis-hermes-v7-dequantized
llama-cli -m ./qwen3.6-35b-a3b-uncensored-genesis-hermes-v7-dequantized/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

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

Downloads and variants (3)

Every published repository of Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized, including quantised re-releases by other authors.

RepositoryFormatDownloads
mradermacher/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized-i1-GGUFGGUF (imatrix)10.7K
mradermacher/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized-GGUFGGUF3.7K
symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantizedsourceTransformers274

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-dequantized 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 symrex/Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V7-dequantized, 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.
  • No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.

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