# Qwen3.6 35B A3B Uncensored HauhauCS Aggressive

URL: https://interfaze.ai/models/hauhaucsqwen36-35b-a3b-uncensored-hauhaucs-aggressive

Qwen3.6 35B A3B Uncensored HauhauCS Aggressive by HauhauCS, a image-text-to-text model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities.

## Comparison

| Feature | Qwen3.6 35B A3B Uncensored HauhauCS Aggressive | Interfaze |
| --- | --- | --- |
| Input Modalities | text, image, video | image, text, audio, video, document |
| Native OCR | No | Yes |
| Long Document Processing | No | Yes |
| Language Support | unknown | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | No | Yes |
| Context Input Size | 262K | 1M |
| Tool Calling | No | Tool calling supported + built in browser, code execution and web search |

### Scaling

| Feature | Qwen3.6 35B A3B Uncensored HauhauCS Aggressive | Interfaze |
| --- | --- | --- |
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)

View model card on [Hugging Face](https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive)

> **[Join the Discord](https://discord.gg/SZ5vacTXYf)** 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](https://huggingface.co/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

-   [HauhauCS on HuggingFace](https://huggingface.co/HauhauCS/models)

## Want more deterministic results?

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)