FocsleFocsle
SI

OpenVLA-Edge

47%
by Stanford IRIS

Edge-distilled OpenVLA. The smallest practical VLA you can put on an AGX Orin without compromising the policy.

Vision-Language-ActionApache-2.0INT8MIXEDvlaopenxrobotics
41K downloads 1.2K deploymentsUpdated Apr 21, 2028
Headline:38.2ms · NVIDIA Jetson Thor · MIXED

About this model

Edge-distilled OpenVLA. The smallest practical VLA you can put on an AGX Orin without compromising the policy.

Authored by stanford-iris. Curated into the Fo’c’sle reference set on 2028-04-21. All cross-chip benchmarks below were collected in matched-pair runs in the HIL lab using the same input pipeline, same upstream preprocessing, and the same downstream consumer. See the methodology page for the full protocol.

Task
Vision-Language-Action
Parameters
7.1 B
Benchmarked on
3 chips
Deployments
1.2K

Architecture

Vision-Language-Action policy
Inferred from upstream weights · simplified
RGB camsProprioGoal textVLM backboneAction headDiscretizerJoint cmds

Headline benchmarks

Training data

Pretrained on the upstream maintainer’s released checkpoint. Edge-distillation pass uses 2.4M frames from the Fo’c’sle distillation corpus (consented public data + opt-in publisher contributions). Quantization-aware fine-tune uses 320K calibration samples drawn from the target task’s eval domain.

  • Pretraining corpus: upstream maintainer release
  • Distillation corpus: 2,400,000 frames
  • Calibration set: 320,000 samples (per task)
  • Eval set: standard benchmark + matched-pair HIL runs