Instructions to use Zoed/Qwen3-Coder-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Zoed/Qwen3-Coder-30B-A3B-Instruct",
	filename="Qwen3-Coder-30B-A3B-Instruct-f16-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 Zoed/Qwen3-Coder-30B-A3B-Instruct with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Zoed/Qwen3-Coder-30B-A3B-Instruct: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 Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Zoed/Qwen3-Coder-30B-A3B-Instruct: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 Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

Use Docker

docker model run hf.co/Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

LM Studio
Jan

vLLM

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Zoed/Qwen3-Coder-30B-A3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Zoed/Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

Ollama
How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with Ollama:
```
ollama run hf.co/Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
```

Unsloth Studio

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct 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 Zoed/Qwen3-Coder-30B-A3B-Instruct 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 Zoed/Qwen3-Coder-30B-A3B-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Zoed/Qwen3-Coder-30B-A3B-Instruct to start chatting

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Zoed/Qwen3-Coder-30B-A3B-Instruct: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": "Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Zoed/Qwen3-Coder-30B-A3B-Instruct: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 Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M
```

Lemonade

How to use Zoed/Qwen3-Coder-30B-A3B-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Zoed/Qwen3-Coder-30B-A3B-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-Coder-30B-A3B-Instruct-Q4_K_M

List all available models

lemonade list

Qwen3-Coder-30B-A3B-Instruct / README.md

Zoed

Upload folder using huggingface_hub

8deec80 verified about 1 month ago

preview code

raw

history blame contribute delete

2.46 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
	base_model_relation: quantized
	language:
	- en
	tags:
	- qwen3
	- qwen3-coder
	- code
	- gguf
	- quantized
	- q4_k_m
	pipeline_tag: text-generation
	---

	# Qwen3-Coder-30B-A3B-Instruct · Q4_K_M GGUF

	This is a Q4_K_M GGUF quantization of [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), produced from the f16 base.

	\| Property \| Value \|
	\|---\|---\|
	\| Base model \| Qwen/Qwen3-Coder-30B-A3B-Instruct \|
	\| Quantization \| Q4_K_M \|
	\| Format \| GGUF \|
	\| Parameters \| 30B (MoE, ~3B active) \|

	## About the base model

	Qwen3-Coder-30B-A3B-Instruct is a Mixture-of-Experts (MoE) code-focused instruction model developed by [Qwen Team, Alibaba Cloud](https://qwenlm.github.io/). It features 30B total parameters with ~3B active parameters per token.

	For full details, see the [original model page](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct).

	## Usage

	### llama.cpp

	```bash
	llama-cli \
	-m Qwen3-Coder-30B-A3B-Instruct-f16-Q4_K_M.gguf \
	--chat-template qwen3 \
	-p "Write a Python function that sorts a list of dictionaries by a given key." \
	-n 512
	```

	### llama-server

	```bash
	llama-server \
	-m Qwen3-Coder-30B-A3B-Instruct-f16-Q4_K_M.gguf \
	--chat-template qwen3 \
	--port 8080
	```

	### Ollama (via Modelfile)

	```
	FROM ./Qwen3-Coder-30B-A3B-Instruct-f16-Q4_K_M.gguf
	PARAMETER num_ctx 32768
	TEMPLATE "{{ ... }}" # use Qwen3 chat template
	```

	## Quantization details

	\| File \| Quant \| Size (approx.) \|
	\|---\|---\|---\|
	\| `Qwen3-Coder-30B-A3B-Instruct-f16-Q4_K_M.gguf` \| Q4_K_M \| ~17 GB \|

	Q4_K_M uses 4-bit quantization with K-quant method on most layers, providing a good balance between size and quality.

	## License

	This quantized model is derived from [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) and is released under the same [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).

	Per Qwen's terms, appropriate credit is given to the original authors:

	> Qwen3-Coder-30B-A3B-Instruct is developed by Qwen Team, Alibaba Cloud.
	> Original model: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct

	## Citation

	```bibtex
	@misc{qwen3coder,
	title = {Qwen3-Coder},
	author = {Qwen Team},
	year = {2025},
	organization = {Alibaba Cloud},
	url = {https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct}
	}
	```