Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive
Qwen3.5-122B-A10B 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. Disclaimers that were present in previous releases have been significantly reduced in this version.
For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
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.
Downloads
| File | Quant | Size |
|---|
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf | Q8_K_P | 145 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf | Q6_K_P | 105 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf | Q6_K | 100 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf | Q5_K_P | 94 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf | Q5_K_M | 87 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf | Q4_K_P | 79 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf | Q4_K_M | 74 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf | IQ4_XS | 65 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf | Q3_K_P | 63 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf | Q3_K_M | 59 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf | IQ3_M | 54 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ3_XXS.gguf | IQ3_XXS | 47 GB |
| Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf | IQ2_M | 40 GB |
| mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf | mmproj (f16) | 867 MB |
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
- 122B total parameters, ~10B 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)
- 48 layers, pattern: 12 x (3 x DeltaNet-MoE + 1 x Attention-MoE)
- 262K native context
- Natively multimodal (text, image, video)
- 248K vocabulary, 201 languages
- Based on Qwen/Qwen3.5-122B-A10B
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:
- Use
--jinja flag with llama.cpp for proper chat template handling
- Thinking mode is on by default — to disable, use
--chat-template-kwargs '{"enable_thinking":false}' or edit the jinja template
- Vision support requires the
mmproj file alongside the main GGUF
Usage
Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.
1# Text only
2llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
3 --jinja -c 131072 -ngl 99
4
5# With vision
6llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
7 --mmproj mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf \
8 --jinja -c 131072 -ngl 99
Other Models
