HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
huggingface.co/HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
Model card
Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
- Join the Discord for updates, roadmaps, projects, or just to chat.
Qwen3.5-35B-A3B uncensored by HauhauCS. 0/465 refusals.
About
No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.
These are meant to be the best lossless uncensored models out there.
Aggressive Variant
Stronger uncensoring — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.
For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
Downloads
| File | Quant | Size | |------|-------|------| | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-BF16.gguf | BF16 | 65 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf | Q8_0 | 35 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 27 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf | Q5_K_M | 24 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 20 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf | IQ4_XS | 18 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf | Q3_K_M | 16 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf | IQ3_M | 15 GB | | Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf | IQ2_M | 11 GB | | mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf | mmproj (f16) | 858 MB |
All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.
Specs
- 35B total parameters, ~3B active per forward pass (MoE)
- 256 experts, 8 routed + 1 shared per token
- Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
- 40 layers, pattern: 10 x (3 x DeltaNet-MoE + 1 x Attention-MoE)
- 262K native context (extendable to 1M with YaRN)
- Natively multimodal (text, image, video)
- Multi-token prediction (MTP) support
- 248K vocabulary, 201 languages
- Based on Qwen/Qwen3.5-35B-A3B
Recommended Settings
From the official Qwen authors:
Thinking mode (default):
- General: temperature=1.0, top_p=0.95, top_k=20, min_p=0, presence_penalty=1.5
- Coding/precise tasks: temperature=0.6, top_p=0.95, top_k=20, min_p=0, presence_penalty=0
Non-thinking mode:
- General: temperature=0.7, top_p=0.8, top_k=20, min_p=0, presence_penalty=1.5
- Reasoning tasks: temperature=1.0, top_p=1.0, top_k=40, min_p=0, presence_penalty=2.0
Important:
- Keep at least 128K context to preserve thinking capabilities
- Use --jinja flag with llama.cpp for proper chat template handling
- Vision support requires the mmproj file alongside the main GGUF
Usage
Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.
```bash # Text only llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \ --jinja -c 131072 -ngl 99
With vision
llama-cli -m Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \ --mmproj mmproj-Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf \ --jinja -c 131072 -ngl 99 ```
Note: LM Studio may show 256x2.6B in the params column instead of 35B-A3B — this is a cosmetic metadata quirk, the model runs correctly.
Other Formats
- GGUF (this repo)
- GPTQ — coming soon