Instructions to use Bedovyy/Qwen3-32B.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bedovyy/Qwen3-32B.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="Bedovyy/Qwen3-32B.w8a8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bedovyy/Qwen3-32B.w8a8")
model = AutoModelForCausalLM.from_pretrained("Bedovyy/Qwen3-32B.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 Bedovyy/Qwen3-32B.w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bedovyy/Qwen3-32B.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": "Bedovyy/Qwen3-32B.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bedovyy/Qwen3-32B.w8a8

SGLang

How to use Bedovyy/Qwen3-32B.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 "Bedovyy/Qwen3-32B.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": "Bedovyy/Qwen3-32B.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 "Bedovyy/Qwen3-32B.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": "Bedovyy/Qwen3-32B.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Bedovyy/Qwen3-32B.w8a8 with Docker Model Runner:
```
docker model run hf.co/Bedovyy/Qwen3-32B.w8a8
```

W8A8 INT8 Quantization of Qwen3-32B

I made this for running on vLLM with Ampere GPU.

On 2xRTX3090, you may set context length to upto 16384 (or 24576 if you use --kv-cache-dtype fp8).

Quantization method

Quantized using

Tool: llmcompressor 0.5.2.dev22 (db959a3).
System: 4x3090, DDR4 128GB + swap 32GB
Time taken: 6 hours (wall time)

## modified based on the code from https://huggingface.co/nytopop/Qwen3-14B.w8a8

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
from llmcompressor.transformers.compression.helpers import calculate_offload_device_map

model_id  = "Qwen/Qwen3-32B"
model_out = "Qwen3-32B.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)

model = AutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
  torch_dtype="bfloat16",
  max_memory={0: "10GiB", 1:"10GiB", 2:"10GiB", 3:"10GiB", "cpu":"96GiB"},
)

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

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

Downloads last month: 6

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for Bedovyy/Qwen3-32B.w8a8

Base model

Qwen/Qwen3-32B

Quantized

(158)

this model