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

By neuromechanist · ↓ 2 · ♥ 0 · Updated 2025-12-29

What's in this repo

This page lists the files in neuromechanist/Qwen3-Embedding-0.6B-ONNX-Q8, including model_uint8.onnx.

1 ONNX models (.onnx files)
10 files, including 6 .json, 1 .md, 1 .txt, 1 .onnx
Last updated 2025-12-29

ONNX files

File	Size	Download
onnx/model_uint8.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

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.

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

Model info

onnx qwen3 region:us

↓ 2 ♥ 0

Created: 2025-12-29

Updated: 2025-12-29

View on Hugging Face

Files (10)

.gitattributes

README.md

added_tokens.json

config.json

merges.txt

onnx/model_uint8.onnx ONNX

special_tokens_map.json

tokenizer.json

tokenizer_config.json

vocab.json

Related models

More from neuromechanist

No other models by this author.

More models

No task type declared.