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

Zoed commited on Apr 28

Commit

8deec80

verified ·

1 Parent(s): f96f130

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +90 -3

README.md CHANGED Viewed

@@ -1,3 +1,90 @@
----
-license: apache-2.0
----

+---
+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}
+}
+```