ONNX Model Zoo

ImgSpace/Qwen3-Embedding-0.6B-Int8

By ImgSpace · ↓ 0 · ♥ 0 · Updated 2026-01-26

What's in this repo

This page lists the files in ImgSpace/Qwen3-Embedding-0.6B-Int8, including Qwen3-Embedding-0.6B.int8.onnx.

  • 1 ONNX models (.onnx files)
  • 11 files, including 4 .json, 2 .txt, 1 .onnx, 1 .md, 1 .py
  • Last updated 2026-01-26

ONNX files

File Size Download
Qwen3-Embedding-0.6B.int8.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 Int8 ONNX

Qwen3-Embedding 0.6B 参数量的 Int8 量化 ONNX 版本，用于文本嵌入（embedding）任务。

模型来源

  • 原始模型：Qwen/Qwen3-Embedding 系列（具体参考官方 Qwen3-Embedding-0.6B）
  • 量化方式：Int8 静态量化
  • 导出格式：ONNX Runtime 兼容

使用方式（Python + ONNX Runtime）

import onnxruntime as ort
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("你的用户名/Qwen3-Embedding-0.6B-Int8-ONNX")
session = ort.InferenceSession("Qwen3-Embedding-0.6B.int8.onnx")

text = "这是一个测试句子"
inputs = tokenizer(text, return_tensors="np")
outputs = session.run(None, dict(inputs))
embedding = outputs[0]          # 通常是 last_hidden_state 或 pooler_output

Model info

onnx qwen3 embedding text-embedding int8 quantized license:apache-2.0 region:us
↓ 0 ♥ 0

Created: 2026-01-26

Updated: 2026-01-26

View on Hugging Face

Files (11)

.gitattributes
Dockerfile
Qwen3-Embedding-0.6B.int8.onnx ONNX
README.md
config.json
main.py
merges.txt
requirements.txt
tokenizer.json
tokenizer_config.json
vocab.json

Related models

More from ImgSpace

No other models by this author.

More models

No task type declared.

Popular models