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.

bash

# Text only
llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
  --jinja -c 131072 -ngl 99

# With vision
llama-cli -m Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf \
  --mmproj mmproj-Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive-f16.gguf \
  --jinja -c 131072 -ngl 99

Sherckuith/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive

About

Aggressive Variant

What are K_P quants?

Downloads

Specs

Recommended Settings

Usage

Other Models

Sherckuith/
Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive