Running the π0.5 VLA model locally on a 16GB RTX 4070 Ti SUPER with APXInf
lxfater · x · 2026-10-27
The author ran Physical Intelligence's π0.5 VLA model (INT8) locally on a 16GB RTX 4070 Ti SUPER — a card not on APXInf's official support list — using the open-source APXInf-robo inference engine plus the LIBERO simulator. No real robot arm was needed: a simulated arm in a MuJoCo kitchen successfully turned on the stove and placed a moka pot. APXInf is a Rust-based edge inference engine targeting VLA models on Jetson Thor/Orin with BF16/FP8/INT8 support.
Related event: π0.5 Runs on a Consumer RTX 4070 Ti SUPER(3 posts)→
More from Embodied
- Tesla Tops Waymo in Austin With 438K Weekly Driverless Miles vs 406K — AccBalanced · 2026-10-27
- Tesla FSD safety report: one major collision per 6M miles, 9x safer than US average — elonmusk · 2026-10-27
- Dream Labs is hiring robot learning researchers in SF, plus security and ops roles — scott_e_reed · 2026-10-27
- Beff Jezos: Elon always frontloads mass production and wins the ramp asymptotically — beffjezos · 2026-10-27
- Bedrock Robotics raises $600M Series C to bring autonomous machines to job sites — bsofman · 2026-10-27
- Bonsai Robotics Ships Fleet Management and Mixed Robots for Farm Tasks — kscottz · 2026-10-27