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

Libraries

How to use unsloth/Qwen3-30B-A3B-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="unsloth/Qwen3-30B-A3B-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-30B-A3B-GGUF")
model = AutoModelForMultimodalLM.from_pretrained("unsloth/Qwen3-30B-A3B-GGUF")

llama-cpp-python

How to use unsloth/Qwen3-30B-A3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="unsloth/Qwen3-30B-A3B-GGUF",
	filename="BF16/Qwen3-30B-A3B-BF16-00001-of-00002.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 unsloth/Qwen3-30B-A3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama-cli -hf unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

How to use unsloth/Qwen3-30B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Qwen3-30B-A3B-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": "unsloth/Qwen3-30B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Qwen3-30B-A3B-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/Qwen3-30B-A3B-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3-30B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/Qwen3-30B-A3B-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Qwen3-30B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Qwen3-30B-A3B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use unsloth/Qwen3-30B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf unsloth/Qwen3-30B-A3B-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": "unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-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 unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use unsloth/Qwen3-30B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL
```

Lemonade

How to use unsloth/Qwen3-30B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Qwen3-30B-A3B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Qwen3-30B-A3B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

UD version for the Q5, Q6 and Q8 quant

#11

by nobita3921 - opened May 4, 2025

Discussion

nobita3921

May 4, 2025

Why does the model not have the UD version of Q5, Q6 and Q8 quant like Gemma-3 models? And what is the difference between Q8_0 and UD_Q8_K_XL ?

shimmyshimmer

Unsloth AI org May 6, 2025

Hi there good suggestion, there's no paticular reason why. It's because we forgot to do it and it was time consuming. We'll do it thanks to your suggestion.

UD Q8 is better than normal Q8

Dampfinchen

May 6, 2025

•

edited May 6, 2025

Hi there good suggestion, there's no paticular reason why. It's because we forgot to do it and it was time consuming. We'll do it thanks to your suggestion.

UD Q8 is better than normal Q8

By the way, it appears the context length is not set correctly.

"40960"

Should be "32768" no?

(Never mind, did some research and thats +8K for a typical prompt. So all good.)

nobita3921

May 8, 2025

Hi there good suggestion, there's no paticular reason why. It's because we forgot to do it and it was time consuming. We'll do it thanks to your suggestion.

UD Q8 is better than normal Q8

Yeah, I checked your UD Q8 and normal Q8. With your UD Q8, you use BF16 for some weight matrices as embedding, Q, K, up, down, gate matrix, etc. Meanwhile, the normal Q8_0 just uses Q8_0 for these matrices. So, this is why your UD Q8 is larger but better than one.

thethinkmachine

May 8, 2025

Yeah, I checked your UD Q8 and normal Q8. With your UD Q8, you use BF16 for some weight matrices as embedding, Q, K, up, down, gate matrix, etc. Meanwhile, the normal Q8_0 just uses Q8_0 for these matrices. So, this is why your UD Q8 is larger but better than one.

Yeah, but the, accuracy gains are negligible at best and having bfloat16 weights also slow down inference as most consumer GPUs aren't designed for crunching them.

CHNtentes

May 9, 2025

Yeah, I checked your UD Q8 and normal Q8. With your UD Q8, you use BF16 for some weight matrices as embedding, Q, K, up, down, gate matrix, etc. Meanwhile, the normal Q8_0 just uses Q8_0 for these matrices. So, this is why your UD Q8 is larger but better than one.

Yeah, but the, accuracy gains are negligible at best and having bfloat16 weights also slow down inference as most consumer GPUs aren't designed for crunching them.

Then you should use UD Q6, since it would use Q8 / BF16 for some weights, so it would be very close to normal Q8 in quality and still smaller.

deleted

May 9, 2025

This comment has been hidden (marked as Resolved)

nobita3921

May 9, 2025

https://huggingface.co/posts/wolfram/819510719695955?image-viewer=819510719695955-BF854EB8D3AE3E1937FDE5CDB709F392C964BE24
So impressive with the performance of Qwen3-30B-A3B-UD-Q4_K_XL.GGUFin the benchmark. It is even better than Deepseek-V3-0324 in full precision. Seems that the performance of UD-Q4_K_X_L is so close to normal Q8_0

CHNtentes

May 9, 2025

https://huggingface.co/posts/wolfram/819510719695955?image-viewer=819510719695955-BF854EB8D3AE3E1937FDE5CDB709F392C964BE24
So impressive with the performance of Qwen3-30B-A3B-UD-Q4_K_XL.GGUFin the benchmark. It is even better than Deepseek-V3-0324 in full precision. Seems that the performance of UD-Q4_K_X_L is so close to normal Q8_0

wondering why mlx quant yields worse quality. I've heard people talking about this...

shimmyshimmer

Unsloth AI org May 10, 2025

We've uploaded them all now

Also with a new improved calibration dataset :)

CC: @balieiro @thinkingmachines @supernovastar @dsafdf @PonderosaSharon @indrazor @eepos @CHNtentes @Dampfinchen @nobita3921 @nhbcizelexzbmnfoke @kaupane

nobita3921

May 11, 2025

We've uploaded them all now

Also with a new improved calibration dataset :)

CC: @balieiro @thinkingmachines @supernovastar @dsafdf @PonderosaSharon @indrazor @eepos @CHNtentes @Dampfinchen @nobita3921 @nhbcizelexzbmnfoke @kaupane

Great work ! Thank @shimmyshimmer .

nobita3921 changed discussion status to closed May 11, 2025

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