Instructions to use QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 with Transformers:

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

pipe = pipeline("text-generation", model="QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8")
model = AutoModelForCausalLM.from_pretrained("QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8")
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

vLLM

How to use QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8

SGLang

How to use QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 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 "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8" \
    --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": "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8",
		"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 "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8" \
        --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": "QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 with Docker Model Runner:
```
docker model run hf.co/QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8
```

Model request - Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4

by djdeniro - opened Sep 8, 2025

Discussion

djdeniro

Sep 8, 2025

This model launched with AMD + VLLM 100% works!

Can you create Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4?

JunHowie

QuantTrio org Sep 9, 2025

•

edited Sep 9, 2025

Thanks for confirming it works 100% on AMD + vLLM!
At the moment we don’t have a pure Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4 build available. In the meantime, you can try our other 4-bit quantized models:

Qwen3-235B-A22B-Instruct-2507-AWQ: https://huggingface.co/QuantTrio/Qwen3-235B-A22B-Instruct-2507-AWQ

Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix: https://huggingface.co/QuantTrio/Qwen3-235B-A22B-Instruct-2507-GPTQ-Int4-Int8Mix

djdeniro

Sep 9, 2025

Int8Mix and AWQ not work with vllm in amd 7900xtx gpu cards, so this is reason why i am create request. anyway, i subscribed to you and thank you for the answer!

JunHowie

QuantTrio org Sep 9, 2025

I don’t think this issue is caused by the model itself. I noticed that some AMD developers recently modified the qwen3_moe.py code in vLLM, which introduced certain problems. I’d recommend waiting until the next official vLLM release (v0.10.2) before trying again. For updates on AMD-related development, please follow this PR:https://github.com/vllm-project/vllm/pull/23994

and，We really appreciate your subscription!

djdeniro changed discussion status to closed Sep 9, 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