# Preprint says output length drives most edge VLM energy use

_Wednesday, August 19, 2026 at 12:00 AM EDT · Science, AI · Latest · Tier 2 — Notable_

A preprint profiling five vision-language models on an RTX 3070 and Jetson Orin NX reports that output-token decoding, rather than visual-token processing, is the main driver of inference time and energy.

The authors found each output token took 11 to 39 times as much wall-clock time as an input token. For fixed-token models, removing all visual tokens saved at most 10% of total energy, while controlling output length saved up to 97% across models from 1 billion to 8 billion parameters.

## Sources

- [cs.AI updates on arXiv.org](https://arxiv.org/abs/2607.09520)

---
Canonical: https://techandbusiness.org/newswire/EMcIfFU9wsKR_ANascVEND
Retrieved: 2026-08-19T10:08:54.314Z
Publisher: Tech & Business (techandbusiness.org)