Instructions to use Helllbos/Qwen3-8B-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Helllbos/Qwen3-8B-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="Helllbos/Qwen3-8B-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Helllbos/Qwen3-8B-INT8")
model = AutoModelForCausalLM.from_pretrained("Helllbos/Qwen3-8B-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 Settings

vLLM

How to use Helllbos/Qwen3-8B-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Helllbos/Qwen3-8B-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": "Helllbos/Qwen3-8B-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Helllbos/Qwen3-8B-INT8

SGLang

How to use Helllbos/Qwen3-8B-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 "Helllbos/Qwen3-8B-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": "Helllbos/Qwen3-8B-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 "Helllbos/Qwen3-8B-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": "Helllbos/Qwen3-8B-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Helllbos/Qwen3-8B-INT8 with Docker Model Runner:
```
docker model run hf.co/Helllbos/Qwen3-8B-INT8
```

Qwen3-8B-Quanto-INT8

INT8 quantized derivative of Qwen3-8B using Optimum Quanto for efficient inference with reduced memory usage.

Model Description

This repository provides an INT8 quantized version of Qwen3-8B created using Optimum Quanto.

The objective of this project is to reduce model size and memory requirements while maintaining strong inference performance for real-world applications.

Features

INT8 Quantization
Reduced Memory Usage
Faster Inference on Supported Hardware
Optimized for AI Assistants
Code Generation
Question Answering
Multilingual Support
Compatible with Hugging Face Transformers

Base Model

Property	Value
Base Model	Qwen3-8B
Original Precision	FP16
Quantized Precision	INT8
Quantization Method	Optimum Quanto
Framework	PyTorch + Transformers
Task	Text Generation

Installation

pip install torch transformers optimum-quanto

Usage

from transformers import AutoTokenizer
from optimum.quanto import QuantizedModelForCausalLM

model_id = "Helllbos/Qwen3-8B-Quanto-INT8"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = QuantizedModelForCausalLM.from_pretrained(model_id)

prompt = "Explain Quantization."

inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(
    **inputs,
    max_new_tokens=200
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Recommended Use Cases

AI Chatbots
Personal AI Assistants
Code Generation
Educational Applications
Research
MLOps Workflows
Local LLM Deployment
API-Based Inference

Hardware Recommendations

Minimum

16 GB RAM
Modern Intel or AMD CPU

Limitations

This repository contains a quantized derivative of the original Qwen3-8B model.
Output quality may differ slightly from the original FP16 model due to quantization.
Performance depends on the inference backend and available hardware.