Instructions to use NobodyWho/Qwen_Qwen3-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NobodyWho/Qwen_Qwen3-4B-GGUF",
	filename="Qwen_Qwen3-4B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NobodyWho/Qwen_Qwen3-4B-GGUF 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 NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NobodyWho/Qwen_Qwen3-4B-GGUF: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 NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NobodyWho/Qwen_Qwen3-4B-GGUF: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 NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NobodyWho/Qwen_Qwen3-4B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NobodyWho/Qwen_Qwen3-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

Ollama
How to use NobodyWho/Qwen_Qwen3-4B-GGUF with Ollama:
```
ollama run hf.co/NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
```

Unsloth Studio

How to use NobodyWho/Qwen_Qwen3-4B-GGUF 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 NobodyWho/Qwen_Qwen3-4B-GGUF 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 NobodyWho/Qwen_Qwen3-4B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NobodyWho/Qwen_Qwen3-4B-GGUF to start chatting

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NobodyWho/Qwen_Qwen3-4B-GGUF: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": "NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NobodyWho/Qwen_Qwen3-4B-GGUF: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 NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf NobodyWho/Qwen_Qwen3-4B-GGUF: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 "NobodyWho/Qwen_Qwen3-4B-GGUF: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 NobodyWho/Qwen_Qwen3-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M
```

Lemonade

How to use NobodyWho/Qwen_Qwen3-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NobodyWho/Qwen_Qwen3-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen_Qwen3-4B-GGUF-Q4_K_M

List all available models

lemonade list

Qwen 3 4B

Qwen 3 is not the latest model in the Qwen series. Qwen 3.5 is now available.

Model Capabilities

Text generation — instruction-following chat model
Tool calling — supports function/tool call syntax
Thinking mode — can show explicit reasoning steps before answering (see Getting Started)
Multilinguality — supports over 100 different languages

The full description can be found at the original model page.

Getting Started

Install NobodyWho:

pip install nobodywho

Run with NobodyWho — the model is downloaded and cached automatically on first use:

from nobodywho import Chat

chat = Chat("huggingface:NobodyWho/Qwen_Qwen3-4B-GGUF/Qwen_Qwen3-4B-Q4_K_M.gguf")
response = chat.ask("What is the capital of Denmark?").completed()
print(response) # Copenhagen!

To enable thinking mode:

chat = Chat(
    "huggingface:NobodyWho/Qwen_Qwen3-4B-GGUF/Qwen_Qwen3-4B-Q4_K_M.gguf",
    template_variables={"enable_thinking": True},
)
response = chat.ask("Solve this step by step: if x + 3 = 7, what is x?").completed()
print(response) # 4

Prefer a manual download (e.g. for the Godot or Flutter binding)? Grab the file through the huggingface UI, or:

wget https://huggingface.co/NobodyWho/Qwen_Qwen3-4B-GGUF/resolve/main/Qwen_Qwen3-4B-Q4_K_M.gguf

and pass the local path instead: Chat("./Qwen_Qwen3-4B-Q4_K_M.gguf").

Benchmarks

Coming soon.

How are these GGUFs different?

These GGUF files serve mainly for NobodyWho inference library and are a way that we can guarantee that they will include all of the necessary info to be truly portable (sampler config, token descriptions, etc.). It is our informal effort to somehow arrive at more standardized GGUF files, which contain everything the runtime needs so that the user can have effortless experience using them, without additional fiddling or patching stuff up for every single model.

Model Details

Property	Value
Parameters	4B
Context length	32,768 tokens
Knowledge cutoff	Unknown
License	Apache 2.0
Base model	Qwen/Qwen3-4B

Credits

GGUF quantizations provided by bartowski. Thanks!

Downloads last month: 321

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for NobodyWho/Qwen_Qwen3-4B-GGUF

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Quantized

(249)

this model

Collection including NobodyWho/Qwen_Qwen3-4B-GGUF

Qwen 3

Collection

3 items • Updated 27 days ago