Chips and edge compute

NVIDIA Jetson AGX Thor (T5000)

United States

The de facto flagship compute for humanoid robots in 2026: 7.5x the AI compute of Orin, 128 GB of memory to run VLA models on-robot, adopted or evaluated by nearly every major humanoid maker including Boston Dynamics, Agility, Figure and OpenAI.

Updated 2026-07-09 · Last verified 2026-07-09

VendorNVIDIA
CountryUS
TypeGPU module
AI perf2070 TFLOPS FP4 (sparse, Blackwell GPU)
Power (W)130
Price (USD)$3,499
AvailabilityGA since August 2025 (dev kit $3,499; production modules shipping)
Memory128 GB LPDDR5X
Form factorSystem-on-module (Jetson T5000) + developer kit; 40-130 W envelope
Applicationshumanoid, AMR, manipulation, healthcare, agriculture, vision
Used byBoston Dynamics Atlas, Agility Robotics Digit, Figure, Amazon Robotics, Unitree H2 Plus, Caterpillar, 1X (evaluating)

Sources : NVIDIA Newsroom (2025-08-25)CNX Software (2025-08-19)NVIDIA (2026-07-09)

← Back to comparator · Chips and edge compute
Christian Verbrugge

Christian Verbrugge · D·Fairy

Bringing a physical AI solution into European industry?

15 years at KUKA on automotive OEM programs (€100M), now focused on edge AI and autonomous agents. I support robotics and embodied AI companies on their EMEA market entry: OEM and Tier 1 access, co-funded pilots, AI Act readiness.

Book an intro call