---
title: "Kyutai releases REKI, a 2.4B robot model with efficient memory"
url: https://www.parallelquant.com/posts/kyutai-releases-reki-a-2-4b-robot-model-with-efficient-memory-2131b0
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/17/meet-kyutai-reki-the-2-4b-vla-model-bringing-efficient-memory-to-robot-manipulation/
published: 2026-10-17T20:22:11.000Z
topics: ["research", "robotics", "open source"]
publisher: "Parallel Quant"
---

# Kyutai releases REKI, a 2.4B robot model with efficient memory

*2026-10-17 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/17/meet-kyutai-reki-the-2-4b-vla-model-bringing-efficient-memory-to-robot-manipulation/)*

Kyutai, with Inria and École des Ponts, released REKI, a 2.4B-parameter vision-language-action (VLA) model for robot manipulation. It is pretrained only on public data and keeps a cheap memory of its recent past. On three out-of-distribution benchmarks, only models about twice its size beat it, and all weights are public.

**Why it matters:** Robot policies often act on the current frame alone, so lightweight memory is a practical gap. A small open model that is competitive with larger ones lowers the barrier for robotics labs that cannot train on proprietary data. It adds to the push to make embodied models cheap enough to run on-device.

**Topics:** research, robotics, open source

---
Read the original: https://www.marktechpost.com/2026/10/17/meet-kyutai-reki-the-2-4b-vla-model-bringing-efficient-memory-to-robot-manipulation/
Canonical: https://www.parallelquant.com/posts/kyutai-releases-reki-a-2-4b-robot-model-with-efficient-memory-2131b0
Published by Parallel Quant — https://www.parallelquant.com