Instructions to use ramblingpolymath/qwen3-30B-A3B-w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ramblingpolymath/qwen3-30B-A3B-w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="ramblingpolymath/qwen3-30B-A3B-w8a8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ramblingpolymath/qwen3-30B-A3B-w8a8")
model = AutoModelForCausalLM.from_pretrained("ramblingpolymath/qwen3-30B-A3B-w8a8")
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 ramblingpolymath/qwen3-30B-A3B-w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ramblingpolymath/qwen3-30B-A3B-w8a8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ramblingpolymath/qwen3-30B-A3B-w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ramblingpolymath/qwen3-30B-A3B-w8a8

SGLang

How to use ramblingpolymath/qwen3-30B-A3B-w8a8 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 "ramblingpolymath/qwen3-30B-A3B-w8a8" \
    --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": "ramblingpolymath/qwen3-30B-A3B-w8a8",
		"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 "ramblingpolymath/qwen3-30B-A3B-w8a8" \
        --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": "ramblingpolymath/qwen3-30B-A3B-w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ramblingpolymath/qwen3-30B-A3B-w8a8 with Docker Model Runner:
```
docker model run hf.co/ramblingpolymath/qwen3-30B-A3B-w8a8
```

Activation Quantization Process

by wantsleep - opened Aug 6, 2025

Discussion

wantsleep

Aug 6, 2025

When I load this quantized model from HuggingFace, am I only loading quantized weights? How does activation quantization work during inference since I didn't change any forward method??

wantsleep

Aug 6, 2025

Also, how can I verify whether activation tensors are actually quantized at runtime?

wantsleep changed discussion status to closed Aug 6, 2025

wantsleep

Aug 6, 2025

This comment has been hidden (marked as Spam)

wantsleep changed discussion status to open Aug 6, 2025

ramblingpolymath

Owner Aug 11, 2025

W8A8 quantization is a weights and activation quantization method. Activation are computed at INT8. When using vLLM not additional configuration is required.

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