Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
Note from braydenh563: Q4_K_M is still Q4_K_P but just renamed so that I can pull it directly into ollama. Same for the others.
See the text-only model (no vision): https://huggingface.co/braydenh563/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggr-Ollama-Text
Join the Discord for updates, roadmaps, projects, or just to chat.
Qwen3.6-35B-A3B uncensored by HauhauCS. 0/465 Refusals.
HuggingFace's "Hardware Compatibility" widget doesn't recognize K_P quants — it may show fewer files than actually exist. Click "View +X variants" or go to Files and versions to see all available downloads.
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 | BPW | Size |
|---|---|---|---|
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf | Q8_K_P | 10.06 | 44 GB |
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf | Q6_K_P | 7.07 | 31 GB |
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf | Q5_K_P | 6.47 | 28 GB |
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf | Q4_K_P | 5.40 | 23 GB |
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf | Q3_K_P | 4.39 | 19 GB |
| Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf | Q2_K_P | 3.46 | 15 GB |
| mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf | mmproj (f16) | — | 899 MB |
All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.
What are K_P quants?
K_P ("Perfect") quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.
A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.
Note: K_P quants may show as "?" in LM Studio's quant column. This is a display issue only — the model loads and runs fine.
Specs
- 35B total parameters, ~3B active per forward pass (MoE)
- 256 experts, 8 routed per token
- Hybrid architecture: linear attention + full softmax attention (3:1 ratio)
- 40 layers
- 262K native context
- Natively multimodal (text, image, video)
- Based on Qwen/Qwen3.6-35B-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
--jinjaflag with llama.cpp for proper chat template handling - Vision support requires the
mmprojfile alongside the main GGUF
Usage
Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.
llama-cli -m Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
--mmproj mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf \
--jinja -c 131072 -ngl 99