Real-time VLA on MacBook

Jialin Lu · luxxxlucy.github.io

April 2026 · in progress

Target

Run π0 (and π0.5) on Mac in realtime rates. Dexmal showed that we can run π0 with 30 Hz on a RTX 4090 — see Running VLAs at Real-time Speed v1 and v2.
Right now my numbers are based on my quite lame M4 MacBook Air. RTX 4090 is a much more powerful card.

Current Status

Worst case: If M4 cannot get there, we will fallback to the dirty road: move to a higher-spec M5 Pro/Max chip. The addition of neural accelerator and much wider memory bandwidth shall get us there.

StateRate
Baseline (Vanilla PyTorch)    ≈ 0.8 Hz
Current≈ 2.4 Hz← いまここ
Near-term target5 Hz
Target30 Hz