You can deploy this model and start earning money today!

neuromechanist/
Qwen3-Embedding-0.6B-ONNX-Q8

Name: Qwen3-Embedding-0.6B-ONNX-Q8
Availability: InStock

onnx

qwen3

Views

No views yet

Qwen3-Embedding-0.6B-ONNX-Q8

Quantized (uint8) version of Qwen3-Embedding-0.6B for use with HED-LSP extension.

Model Details

Base Model: Qwen/Qwen3-Embedding-0.6B
ONNX Conversion: onnx-community/Qwen3-Embedding-0.6B-ONNX
Quantization: uint8 (8-bit integer)
Size: ~600 MB (vs 7.8 GB full model)

Usage

This model is used by the HED-LSP VS Code extension for semantic search in HED tag autocomplete.

javascript

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

const extractor = await pipeline('feature-extraction', 'neuromechanist/Qwen3-Embedding-0.6B-ONNX-Q8', {
  dtype: 'q8',
});

License

Apache 2.0 (same as original Qwen model)

Acknowledgments

Qwen Team for the original embedding model
ONNX Community for the ONNX conversion