Instructions to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

LM Studio
Jan
Ollama
How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Ollama:
```
ollama run hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
```

Unsloth Studio

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive to start chatting

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Docker Model Runner:
```
docker model run hf.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M
```

Lemonade

How to use HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q4_K_M

List all available models

lemonade list

New discussion

Resources

View closed (10)

Discord server

pinned

👍 1

#42 opened 4 months ago by

HauhauCS

Suggestion: Add a Human-Friendly Model Summary

#59 opened 30 days ago by

shocker69

Fix pipeline tag (it was missing)!

#58 opened about 2 months ago by

MihaiPopa-1

Safetensors

#57 opened about 2 months ago by

Lexter3000

Request: DOI

#56 opened about 2 months ago by

joko0120

MTP layers mising?

👍 2

#55 opened about 2 months ago by

btearspell

Update metadata (qwen35.embedding_length, qwen35.ssm.inner_size)

#54 opened about 2 months ago by

renhip

Update metadata (qwen35.context_length, qwen35.embedding_length, qwen35.ssm.inner_size)

#53 opened about 2 months ago by

renhip

No output after reasoning

#51 opened 2 months ago by

julez122

error on LM Studio

#50 opened 3 months ago by

mrwassatt1991

Best settings?

#49 opened 3 months ago by

tokat

Disabling thinking output in Comfy-ui in Qwen Nodes

#47 opened 4 months ago by

Thrakks

Legendary model

👍 4

#46 opened 4 months ago by

ussaaron

For the reverse inference of NSFW images, which model's inference result for the model type is the best?

👍 1

#45 opened 4 months ago by

zun75

convert gguf to hf repo format

#44 opened 4 months ago by

som3207

Qwen3.5-9B-Uncensored-HauhauCS-Aggressive repetition of the message.

#41 opened 4 months ago by

Babe191919191

Report

#40 opened 4 months ago by

salfetky

500 error-ollama

👍 9

#39 opened 4 months ago by

XtaZa

Ollama error 500

#38 opened 4 months ago by

WeAreShadows

Error when pulling with Ollama

👍 3

#37 opened 4 months ago by

KingyWolf

May I ask how you make it uncensored without changing database?

#35 opened 4 months ago by

sdasdjasdoasd

How do I launch this model in Xinference?

#34 opened 4 months ago by

JJNEW

error report：Qwen3.5-9B-Uncensored-HauhauCS-Aggressive

#33 opened 4 months ago by

tuge9130

Any chance to get JSON config files?

#31 opened 5 months ago by

ZoontF

Base vs Uncensored Is It Different?

#29 opened 5 months ago by

technowhz

Dose this model support tool calling？

#27 opened 5 months ago by

danielyf2023

MLX Support

➕ 1

#26 opened 5 months ago by

Smulik

Koboldcpp can't load the GGUF variants of this model

#25 opened 5 months ago by

IggyLux

The image part of model still fails on generation in LM Studio

👀 1

#24 opened 5 months ago by

jodi42

exl3 support

#19 opened 5 months ago by

sdffewe

Is this based on the final quantization optimization version of unsloth?

#17 opened 5 months ago by

wzgrx

great work!

#16 opened 5 months ago by

kalota

It cann't launch by ollama

#15 opened 5 months ago by

ymilv

languages support are still the same ?

#14 opened 5 months ago by

takadk

thinking mode help

#13 opened 5 months ago by

wicesxs

Any tips how to make this work in ollama?

#12 opened 5 months ago by

Quasimondo

languages support are still the same ?

#11 opened 5 months ago by

pikkaa

IQ and MXFP4 quants?

#9 opened 5 months ago by

ampersandru

Speculative Decoding.

#8 opened 5 months ago by

Sinaya

Excellent work! Do you share any of your methodology or no?

#5 opened 5 months ago by

g0t4

Plans for 122B?

👍 1

#4 opened 5 months ago by

SerySmith

Appreciate for sharing, the effect is excellent. Please upload the original safetensors format model if you could.

👍 4

#2 opened 5 months ago by

wakewick

Very good model. Request for support for models with more specifications.

👍 3

#1 opened 5 months ago by

wzgrx