Qwen3-0.6B-onnx

Qwen3-0.6B ONNX Model

This is an ONNX format conversion of the Qwen/Qwen3-0.6B model, optimized for inference with ONNX runtime.

Model Details

• Base Model: Qwen/Qwen3-0.6B
• Architecture: Qwen3ForCausalLM
• Converted By: [waynewangchn00]
• Conversion Tool: optimum-cli export onnx

Model Specifications

• Hidden Size: 1024
• Number of Layers: 28
• Attention Heads: 16
• Max Position Embeddings: 40960
• Vocabulary Size: 151936

License

This model inherits the Apache 2.0 License from the original Qwen/Qwen3-0.6B model.

Usage

Python (ONNX Runtime)

from optimum.onnxruntime import ORTModelForCausalLM

model = ORTModelForCausalLM.from_pretrained("path/to/qwen3_0_6b_onnx")

JavaScript (Transformers.js)

import { pipeline } from '@xenova/transformers';

// Load the ONNX model
const generator = await pipeline(
    'text-generation',
    'path/to/qwen3_0_6b_onnx',
    {
        quantized: false,
        model_file: 'model.onnx'
    }
);

// Generate text
const output = await generator('Hello world');
console.log(output);

Original Model Information

For more details about the original model, please refer to:

• Qwen/Qwen3-0.6B at Hugging Face
• Qwen GitHub Repository