fredrezones55/ Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive:Q2_K_P

5,999 3 days ago

Qwen3.6-35B-A3B uncensored by HauhauCS. 0/465 Refusals. Patched to have vision support; 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.

vision tools thinking 
ollama run fredrezones55/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive:Q2_K_P

Details

4 days ago

9a524a0e7756 · 16GB ·

model
qwen35moe
·
35.1B
·
Q2_K
template
{{ .Prompt }}
params
{ "min_p": 0, "presence_penalty": 1.5, "repeat_penalty": 1, "temperature": 1, "t

Readme

繋 ollama bridge patched gguf model to restore support for gguf vision.

Noting: apparently even tool calling at 2-bit quant is strong. https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF/discussions/2

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive

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
— Q8_0 8.5 —
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf Q6_K_P 7.07 31 GB
— Q6_K 6.6 —
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf Q5_K_P 6.47 28 GB
— Q5_K_M 5.7 —
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-Q4_K_M.gguf Q4_K_M 4.88 21 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_NL.gguf IQ4_NL 4.56 20 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf IQ4_XS 4.32 19 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf Q3_K_P 4.39 19 GB
— Q3_K_M 3.9 —
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf IQ3_M 3.56 15 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf Q2_K_P 3.46 15 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-IQ2_M.gguf IQ2_M 2.69 11 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 --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.

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

Other Models