Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V13
35BQwenuncensored
from HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
↓ 924.6K♥ 597
Hermes3.6-35B-A3B-Uncensored-Genesis
Hermes3.6-35B-A3B-Uncensored-Genesis is a abliterated and uncensored variant of HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive, published on Hugging Face by jan1k. 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 32.1K downloads.
Specification
- Model name
- Hermes3.6-35B-A3B-Uncensored-Genesis
- Source repository
- jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF
- Publisher
- jan1k
- Parameters
- 35B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 1 Sept 2026
- Last updated
- 5 Sept 2026
Ablation technique
How Hermes3.6-35B-A3B-Uncensored-Genesis 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
“This repository contains the NVFP4 (NVIDIA 4-bit Floating Point) quantized GGUF releases of LuffyTheFox's Hermes 3.6 / Qwen 3.6 35B A3B Uncensored Genesis series, including the Genesis Final Release.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF --local-dir ./hermes3.6-35b-a3b-uncensored-genesis
llama-cli -m ./hermes3.6-35b-a3b-uncensored-genesis/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of Hermes3.6-35B-A3B-Uncensored-Genesis.
| Repository | Format | Downloads |
|---|---|---|
| jan1k/Hermes3.6-35B-A3B-Uncensored-Genesis-NVFP4-GGUFsource | GGUF | 32.1K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Hermes3.6-35B-A3B-Uncensored-Genesis 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 Hermes3.6-35B-A3B-Uncensored-Genesis is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with jan1k, and does not independently verify publisher claims. See responsible use.