InstinctFlash: Run 5B world-action models in real time on Jetson Thor

Show HN: InstinctFlash – Run 5B world-action models in real time on Jetson Thor

General-Instinct open-sourced InstinctFlash, a high-performance inference runtime built for robotics models. It runs 5B-parameter world-action models in real time on an NVIDIA Jetson Thor edge device, with perception-to-action latency at 11 ms. The repo is an early public release—code and docs are still being assembled. The post doesn't spell out which robot platforms are supported, where to get model weights, or what other hardware is compatible beyond Jetson Thor.

Why it matters: 5B model at 11ms on Jetson Thor is a solid number — H and K both hold up. But the repo is early-stage, docs and platform support aren't spelled out, and R only reaches the robotics crowd, so it lands right at the featured threshold at 72.