Jetson Orin Nano Super
67 TOPS in 25 W for under $250. The moment your perception needs a real neural network at frame rate, this replaces the Pi and everything suddenly fits in the time budget.
The role it plays
Every serious robot needs two tiers. A microcontroller owns the control loop at a fixed rate with hard deadlines, because a missed deadline is a visible jolt. A Linux or GPU board owns perception, planning and networking, because those are bursty and best-effort. Nothing balance-critical belongs on the Linux side.
Typical use: On-robot VSLAM, VLA models, multi-camera perception.
What the numbers actually mean
The headline figure is 67 TOPS (INT8, sparse) (ai performance), with 1024-core Ampere as the next most load-bearing number (gpu). At $249 in the compute tier it sits in the mid range: enough money that you should plan the mounting and wiring before ordering, but not so much that one mistake ends the project.
How it compares
Same subsystem, closest alternatives. The primary spec column is usually the one that decides it.
| Part | Price | Primary spec | Second spec |
|---|---|---|---|
| Jetson Orin Nano SuperEdge GPU | $249 | 67 TOPS (INT8, sparse) | 1024-core Ampere |
| Raspberry Pi 5 (8 GB)SBC, high-level brain | $80 | 4× Cortex-A76 @ 2.4 GHz | 8 GB LPDDR4X |
| Jetson Orin NX 16 GBEdge GPU | $499 | 100 TOPS (INT8, sparse) | 1024-core Ampere |
| ESP32-S3Real-time MCU + Wi-Fi | $5 | 2× Xtensa LX7 @ 240 MHz | 512 KB SRAM + 8 MB PSRAM typical |
| Teensy 4.1High-performance MCU | $32 | Cortex-M7 @ 600 MHz, hardware FPU | 1 MB + 8 MB PSRAM (optional) |
Where it shows up
Platforms in this atlas that use something in this class: Berkeley Humanoid Lite.