// HACKER NEWS — CYBERSECURITY
Show HN: InstinctFlash – Run 5B world-action models in real time on Jetson Thor
A high-performance serving framework for robotics models.
Prediction p50 on Jetson Thor (ms), measured September 15, 2026.
We’ve seen up to 33.78× speedup with no observed loss in task performance in our real-robot tests.
VA measures early continuations; each row compares the same schedule.
The 33.78× headline includes 25V/50A → 2V/4A.
FP8 and sampling changes are optional.
Protocol and raw results · Native VA 2V/4A · Reproduction commands
The Python 3.10+ core inspects checkpoints and plans without PyTorch or a GPU.
Inference uses a separate, pinned environment for each model family. For RTX 4090:
Use va, vla4, vla2, pi05, groot, edge, nano or dreamzero.
Edge and Nano use Python 3.13; the other families use Python 3.12.
The bootstrap installs the upstream source, compatibility patches, core and adapter.
Model weights are downloaded separately. See RTX 5090 setup,
RTX 4090 setup
or Jetson Thor setup, which selects --target jetson_thor
and uses the Thor CUDA backend build.
Your fine-tuned checkpoint — the expected case. Point serve at the training output; it
detects the family, writes the small instinctflash.json declaration from what the checkpoint
itself proves, and starts serving. One command:
Anything the checkpoint cannot prove is asked for explicitly, never guessed. Once the
declaration exists (serve writes it on first run), the same directory also loads in Python:
A stock release — use its Hub id after installing the family's environment: