# Using Large ONNX Models with External Data in Vespa Embedders

DevFeed: [Using Large ONNX Models with External Data in Vespa Embedders](<https://devfeed.tech/articles/using-large-onnx-models-with-external-data-in-vespa-embedders-12794.md>)

Original publisher: [Read original article](<https://blog.vespa.ai/onnx-external-data-in-vespa-embedders/>)

Author: bjorncs thomas

Published: 2026-03-27T00:00:00Z

Content type: tutorial

Language: en

Sources: [Vespa Blog](<https://devfeed.tech/sources/vespa-blog.md>)

Topics: [onnx](<https://devfeed.tech/topics/onnx.md>), [Cloud](<https://devfeed.tech/topics/cloud.md>)

Tags: [authentication](<https://devfeed.tech/tags/authentication.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [files](<https://devfeed.tech/tags/files.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [models](<https://devfeed.tech/tags/models.md>), [onnx](<https://devfeed.tech/tags/onnx.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [serialization-format](<https://devfeed.tech/tags/serialization-format.md>)

## AI overview

Vespa embedders now support large ONNX models whose weights are stored in external data files. Starting with Vespa 8.544, Vespa automatically downloads referenced external files when loading URL-based models, with support for private models through propagated authentication tokens. The feature is limited to embedders and supported model references.

## Source excerpt

Many ONNX models exceed the 2GB protobuf limit and store weights in external data files. Vespa now supports these models for embedders.