Qwen3-4B-2507-Instruct-Aggressive

Instructions to use nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M

LM Studio
Jan
Ollama
How to use nazihara/Qwen3-4B-2507-Instruct-Aggressive with Ollama:
```
ollama run hf.co/nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
```
Unsloth Desktop

How to use nazihara/Qwen3-4B-2507-Instruct-Aggressive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use nazihara/Qwen3-4B-2507-Instruct-Aggressive with Docker Model Runner:
```
docker model run hf.co/nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M
```

Lemonade

How to use nazihara/Qwen3-4B-2507-Instruct-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-2507-Instruct-Aggressive-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-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 nazihara/Qwen3-4B-2507-Instruct-Aggressive:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nazihara/Qwen3-4B-2507-Instruct-Aggressive with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf nazihara/Qwen3-4B-2507-Instruct-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 "nazihara/Qwen3-4B-2507-Instruct-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"

Qwen3-4B-2507-Instruct-Aggressive / README.md

nazihara

HauhauCS

Duplicate from HauhauCS/Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive

24d5e69 6 months ago

preview code

Raw

History Blame Contribute Delete

1.83 kB

	---
	license: apache-2.0
	tags:
	- uncensored
	- qwen3
	language:
	- en
	- zh
	base_model: Qwen/Qwen3-4B-Instruct-2507
	---

	# Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive

	> [Join the Discord](https://discord.gg/SZ5vacTXYf) for updates, roadmaps, projects, or just to chat.

	Qwen3 4B 2507 Instruct uncensored by HauhauCS.

	## 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 vs Balanced

	Aggressive applies stronger uncensoring. Use this when you need no refusals.


	## Downloads

	\| File \| Quant \| Size \|
	\|------\|-------\|------\|
	\| Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive-FP16.gguf \| FP16 \| 7.5 GB \|
	\| Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive-Q8_0.gguf \| Q8_0 \| 4.0 GB \|
	\| Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive-Q6_K.gguf \| Q6_K \| 3.1 GB \|
	\| Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \| Q4_K_M \| 2.4 GB \|

	## Specs

	- 4B parameters (dense)
	- 262K context
	- Based on [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)

	## Recommended Settings

	From the Qwen team:

	Thinking mode (default):
	- `temperature=0.6`
	- `top_p=0.95`
	- `top_k=20`
	- `min_p=0`

	Non-thinking mode:
	- Add `/no_think` at the end of your prompt, or
	- `temperature=0.7`
	- `top_p=0.8`
	- `top_k=20`
	- `min_p=0`

	Important:
	- Use `--jinja` flag for proper chat template handling
	- Thinking mode produces `<think>...</think>` tags before responses

	## Usage

	Works with llama.cpp, LM Studio, Jan, koboldcpp, Ollama, etc.

	```bash
	# llama.cpp example
	./llama-cli -m Qwen3-4B-2507-Instruct-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
	-p "Hello" --jinja -c 8192
	```