AxForge
Sign in Get started

Model reference · open weights

e5-small-onnx

Embeddings nixiesearch Embeddings 1 build Open weights 3k dl/mo

e5-small-onnx is an open-weight embedding model from nixiesearch.

  • e5-small-onnx is a sentence-transformers model by nixiesearch designed for feature extraction tasks such as clustering and semantic search.
  • It maps English sentences and paragraphs to a dense vector space with a context length of 512 tokens.
  • The model is available in Float32 and QInt8 quantized ONNX formats and is released under the Apache 2.0 license.

Summary of the nixiesearch/e5-small-v2-onnx model card, 2026-10-01

Hugging Face ↗

What it is

Released bynixiesearch
Released2023-08-07

From the model card

What nixiesearch says about e5-small-onnx

Read the model card

This is a sentence-transformers model: It maps sentences & paragraphs to a N dimensional dense vector space and can be used for tasks like clustering or semantic search.

The model conversion was made with onnx-convert tool with the following parameters:

python convert.sh --model_id intfloat/e5-small-v2 --quantize QInt8 --optimize 2

There are two versions of model available:

  • model.onnx - Float32 version, with optimize=2
  • model_opt2_QInt8.onnx - QInt8 quantized version, with optimize=2

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms