Qwen3.8-27B-Uncensored
27BQwenuncensoredgated
from Qwen/Qwen3.8-27B
↓ 3.6M♥ 1.4K81 repos
Qwen3.5-35B-A3B-Uncensored-FernflowerAI
Qwen3.5-35B-A3B-Uncensored-FernflowerAI is a abliterated and uncensored variant of HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive, published on Hugging Face by mudler. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 5 repositories in MLX and GGUF formats, totalling 11.2K downloads.
Specification
- Model name
- Qwen3.5-35B-A3B-Uncensored-FernflowerAI
- Source repository
- mudler/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUF
- Publisher
- mudler
- Parameters
- 35B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- MLX, GGUF
- First indexed
- 10 Apr 2026
- Last updated
- 17 Aug 2026
Ablation technique
How Qwen3.5-35B-A3B-Uncensored-FernflowerAI 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
“💚 Big thanks to Hugging Face for generously donating additional storage, much appreciated.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mudler/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUF --local-dir ./qwen3.5-35b-a3b-uncensored-fernflowerai
llama-cli -m ./qwen3.5-35b-a3b-uncensored-fernflowerai/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "mudler/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve mudler/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUF --trust-remote-codeDownloads and variants (4)
Every published repository of Qwen3.5-35B-A3B-Uncensored-FernflowerAI, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| mudler/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUFsource | GGUF | 9.3K |
| froggeric/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-8bit | MLX | 1.6K |
| froggeric/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-4bit | MLX | 245 |
| wazimondo/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-APEX-GGUF | GGUF | 105 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.5-35B-A3B-Uncensored-FernflowerAI 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/Qwen3.5-35B-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/Qwen3.5-35B-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 Qwen3.5-35B-A3B-Uncensored-FernflowerAI is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with mudler, and does not independently verify publisher claims. See responsible use.