# Simplexity Robotics releases and open-sources world-action model SimpleWAM, with 6B model achieving on-device inference as low as 42.31ms

- Source: 至简动力 · 微信公众号
- Published: 2026-09-28T14:37:43.000Z
- RoboHot: https://robohot.news/en/items/u9gwus8qvje3rgy60m7ru8i6t
- Original: https://mp.weixin.qq.com/s?__biz=MzYzMTMyMTIyMw==&mid=2247484445&idx=1&sn=7497fc6a92abcef815d1bedcf0469037&chksm=f16e716fe411bcef452e36aa5dc654156316a169017ff65880e801b7038d3c61f7c45c8ebba9&scene=126&sessionid=1792409738#rd

## Summary

Simplexity Robotics has launched and open-sourced the world-action model SimpleWAM; the 6B-parameter version reduces inference latency on NVIDIA ThorX (T5000) from 181.23ms to 42.31ms, enabling high-frequency closed-loop operation on-device at nearly 24Hz.

## Why it matters

The original article presents the on-device optimization path from 181ms to 42ms and four architectural designs, which can be transferred to understand how world-action models can meet high-frequency closed-loop control requirements.