Instructions to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF",
	filename="Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-F16-00001-of-00003.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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-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": "rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

Ollama
How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with Ollama:
```
ollama run hf.co/rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF to start chatting

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

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": "rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

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 rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with Docker Model Runner:
```
docker model run hf.co/rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL
```

Lemonade

How to use rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull rodrigomt/Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-Thinking-Deepseek-Distill-2507-v3.1-V2-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Q5 Q6 Q8 k_xl?

by Trilogix1 - opened Oct 4, 2025

Discussion

Trilogix1

Oct 4, 2025

I am particularly founded to this model. Would you consider to the other quantizations it may come out smth better.

Thanks in advance :)

rodrigomt

Owner Oct 6, 2025

Hey!

Based on my practical experience with Qwen3-Coder-30B-A3B-Instruct-480b-Distill and Qwen3-30B-A3B-Thinking-Deepseek-Distill in the Q4_K_XL variant, I'd say this format strikes an excellent balance between performance and hardware efficiency.

In daily use, the Coder version is the one I use most. Even when quantized to Q4_K_XL (to obtain 64k context) and run within VSCode with Cline, it still generates Python, JavaScript, and Dart code (the languages I work with) with almost no errors. From what I've observed, it clearly outperforms the standard Qwen3-Coder-30B, demonstrating good consistency and decent autocorrection. It's certainly not on par with the respective teacher models, but it's capable of handling everyday tasks.

What makes Unsloth's "XL" quantization particularly interesting is that it doesn't quantize all layers uniformly; some of the most critical ones are quantized at Q5, while the less sensitive layers remain at Q4. In practice, this makes the Q4_K_XL behave much closer to a Q5 than a typical Q4.

Therefore, when compared to the standard Q5, Q6, or even Q8 versions, the XL tends to offer better overall efficiency and perceptual quality, making it a balanced choice for performance without sacrificing too much hardware.

When I have time, I still plan to test the Q5, Q6, and Q8 versions in XL and release them on Hugging Face.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment