Instructions to use Qwen/Qwen3-4B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-4B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Qwen/Qwen3-4B-GGUF",
	filename="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

llama.cpp

How to use Qwen/Qwen3-4B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Qwen/Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 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-server -hf Qwen/Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf 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 Qwen/Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf 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 Qwen/Qwen3-4B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Qwen/Qwen3-4B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Qwen/Qwen3-4B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use 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 "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": "Qwen/Qwen3-4B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-4B-GGUF:Q4_K_M

Ollama
How to use Qwen/Qwen3-4B-GGUF with Ollama:
```
ollama run hf.co/Qwen/Qwen3-4B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use 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 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 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 Qwen/Qwen3-4B-GGUF to start chatting

Pi new

How to use 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-server -hf 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": "Qwen/Qwen3-4B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use 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-server -hf 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 Qwen/Qwen3-4B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Qwen/Qwen3-4B-GGUF with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-4B-GGUF:Q4_K_M
```

Lemonade

How to use Qwen/Qwen3-4B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Qwen/Qwen3-4B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3-4B-GGUF

Qwen3 Highlights

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:

Uniquely support of seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within single model, ensuring optimal performance across various scenarios.
Significantly enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
Superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
Expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
Support of 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.

Model Overview

Qwen3-4B has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 4.0B
Number of Paramaters (Non-Embedding): 3.6B
Number of Layers: 36
Number of Attention Heads (GQA): 32 for Q and 8 for KV
Context Length: 32,768 natively and 131,072 tokens with YaRN.
Quantization: q4_K_M, q5_0, q5_K_M, q6_K, q8_0

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Quickstart

llama.cpp

Check out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp. In the following demonstration, we assume that you are running commands under the repository llama.cpp.

./llama-cli -hf Qwen/Qwen3-4B-GGUF:Q8_0 --jinja --color -ngl 99 -fa -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 40960 -n 32768 --no-context-shift

ollama

Check out our ollama documentation for more usage guide.

You can run Qwen3 with one command:

ollama run hf.co/Qwen/Qwen3-4B-GGUF:Q8_0

Switching Between Thinking and Non-Thinking Mode

You can add /think and /no_think to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.

Here is an example of multi-turn conversation:

> Who are you /no_think

<think>

</think>

I am Qwen, a large-scale language model developed by Alibaba Cloud. [...]

> How many 'r's are in 'strawberries'? /think

<think>
Okay, let's see. The user is asking how many times the letter 'r' appears in the word "strawberries". [...]
</think>

The word strawberries contains 3 instances of the letter r. [...]

Processing Long Texts

Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the YaRN method.

To enable YARN in llama.cpp:

./llama-cli ... -c 131072 --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768

All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. We advise adding the rope_scaling configuration only when processing long contexts is required. It is also recommended to modify the factor as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set factor as 2.0.

The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.

Best Practices

To achieve optimal performance, we recommend the following settings:

Sampling Parameters:
- For thinking mode (enable_thinking=True), use Temperature=0.6, TopP=0.95, TopK=20, MinP=0, and PresencePenalty=1.5. DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions.
- For non-thinking mode (enable_thinking=False), we suggest using Temperature=0.7, TopP=0.8, TopK=20, MinP=0, and PresencePenalty=1.5.
- We recommend setting presence_penalty to 1.5 for quantized models to suppress repetitive outputs. You can adjust the presence_penalty parameter between 0 and 2. A higher value may occasionally lead to language mixing and a slight reduction in model performance.
Adequate Output Length: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.
- Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the answer field with only the choice letter, e.g., "answer": "C"."
No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}