Instructions to use cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit")
model = AutoModelForCausalLM.from_pretrained("cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit

SGLang

How to use cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit 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 "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit" \
    --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": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit",
		"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 "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit" \
        --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": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit with Docker Model Runner:
```
docker model run hf.co/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit
```

GPU memory utilization

by ojigrande - opened Feb 17

Discussion

ojigrande

Feb 17

I'm trying to run by vllm on Orin. It gives me an error:

ValueError: Free memory on device cuda:0 (41.83/61.37 GiB) on startup is less than desired GPU memory utilization (0.8, 49.09 GiB).

But your description states that the model takes up 17G.
Explain what I'm doing wrong?

cpatonn

cyankiwi org Feb 17

Thank you for using my model! In addition to the 17 GB model memory size, vllm will require some additional memory allocation for KV cache.

However, in your specific case, it seems that your gpu_memory_utilization value is too high, and lowering it should solve the problem.

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