Instructions to use nytopop/Qwen3-8B.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nytopop/Qwen3-8B.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="nytopop/Qwen3-8B.w8a8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nytopop/Qwen3-8B.w8a8")
model = AutoModelForCausalLM.from_pretrained("nytopop/Qwen3-8B.w8a8", 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 nytopop/Qwen3-8B.w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nytopop/Qwen3-8B.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": "nytopop/Qwen3-8B.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nytopop/Qwen3-8B.w8a8

SGLang

How to use nytopop/Qwen3-8B.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 "nytopop/Qwen3-8B.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": "nytopop/Qwen3-8B.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 "nytopop/Qwen3-8B.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": "nytopop/Qwen3-8B.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nytopop/Qwen3-8B.w8a8 with Docker Model Runner:
```
docker model run hf.co/nytopop/Qwen3-8B.w8a8
```

Int8 quant for optimized performance on Ampere.

usage

uv venv --python 3.12

uv pip install sglang[all] --find-links https://flashinfer.ai/whl/cu124/torch2.5/flashinfer-python

uv run python -m sglang.launch_server --model-path nytopop/Qwen3-8B.w8a8 --quantization w8a8_int8 --reasoning-parser qwen3

creation

from transformers import AutoTokenizer, AutoModelForCausalLM
from datasets import load_dataset
from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier

model_id  = "Qwen/Qwen3-8B"
model_out = "Qwen3-8B.w8a8"

num_samples = 256
max_seq_len = 4096

tokenizer = AutoTokenizer.from_pretrained(model_id)

def preprocess_fn(example):
  return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)}

ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
ds = ds.shuffle().select(range(num_samples))
ds = ds.map(preprocess_fn)

recipe = [
  SmoothQuantModifier(smoothing_strength=0.7),
  GPTQModifier(sequential=True,targets="Linear",scheme="W8A8",ignore=["lm_head"],dampening_frac=0.01),
]

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
  torch_dtype="bfloat16",
)

oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=max_seq_len,
  num_calibration_samples=num_samples,
  output_dir=model_out,
)