What can I run on Jetson Orin Nano 8GB (Super)?
8 GB unified memoryAmpere (1024 CUDA cores, 32 Tensor Cores)67 INT8 TOPS (Super Developer Kit; up from 40 TOPS before the JetPack 6.2 Super update)7W–25W (MAXN_SUPER mode has no fixed power budget)View matrix for this target →
One entry for the Orin Nano 8GB module and its developer kit. The 'Super' developer kit is the same hardware: JetPack 6.2+ adds the 25W and MAXN_SUPER power modes (MAXN_SUPER only when flashed with the jetson-orin-nano-devkit-super configuration), raising the headline from 40 to 67 TOPS and memory bandwidth from 68 to 102 GB/s. Power mode and clock pinning (jetson_clocks) change inference latency materially, so runs on this target must record platform.power_mode and the JetPack version. 8 GB is unified memory shared with the OS and CPU.
Policy by policy
| Policy | Params | Inference memory (sourced, with precision) | On Jetson Orin Nano 8GB (Super) | Best measured |
|---|---|---|---|---|
| Evo-1 VLA | 770M | — | measured | 3.45 Hz · ONNX (split) · fp16 · 1 cam |
| GR00T N1.7 VLA | 3B | ≥16 GB | measured | 3.66 Hz · TensorRT · fp16 · 3 cam |
| SmolVLA VLA | 450M | 1.75 GB measured fp32 | measured | 9.3 Hz · TensorRT · fp16 · 2 cam |
| X-VLA VLA | 900M | — | measured | 2.92 Hz · TensorRT · fp16 · 3 cam |
| π0.5 VLA | — | ≥8 GB | measured | 2.28 Hz · TensorRT · fp16 · 2 cam |
| LingBot-VA World model | 5.3B | ≥18 GB | T4 inferred · exceeds memory | needs ≥18 GB |
| OpenVLA-OFT VLA | — | ≥16 GB | T4 inferred · exceeds memory | needs ≥16 GB |
| ACT Imitation | 80M | 211 MB measured fp32 | no data | |
| Diffusion Policy Imitation | — | 1.12 GB measured fp32 | no data | |
| EO-1 VLA | 3B | ≥6.5 GB | no data | |
| Fast-WAM World model | 6B | — | no data | |
| HIL-SERL RL | — | — | no data | |
| MolmoAct2 VLA | — | 12.1 GB measured bf16 | no data | |
| Multitask DiT Imitation | 450M | — | no data | |
| OpenVLA VLA | 7.5B | 15 GB measured bf16 | no data | |
| TD-MPC RL | — | — | no data | |
| VLA-JEPA VLA | — | — | no data | |
| VQ-BeT Imitation | — | — | no data | |
| WALL-OSS VLA | — | — | no data | |
| π0 VLA | 3.3B | 13.32 GB measured fp32 | no data | |
| π0-FAST VLA | — | ≥8 GB | no data |
“Exceeds memory” compares a policy's upstream-stated minimum inference memory (never a measured peak, which is precision-specific) with this target's unified (shared CPU/GPU) memory, so the real budget is lower. It is arithmetic, not observation, and is labelled inferred. Quantised or split runtimes can change the answer; a measured run always wins.
All measured runs on Jetson Orin Nano 8GB (Super)
| Policy | Runtime | Precision | Cams | p50 / p95 ms | Inference | Platform | Source |
|---|---|---|---|---|---|---|---|
| SmolVLA | TensorRT | fp16 | 2 @640x480 | 107.55 / 108.48 | 9.3 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 512x512; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 1.78 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| SmolVLA | ONNX (split) | fp16 | 2 | 189.89 / 190.93 | 5.25 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Configured EP priority 7 graphs TensorRT / 2 CPU. System RAM 2385 MB in use. | T3 · community reported |
| GR00T N1.7 | TensorRT | fp16 | 3 @640x480 | 273.7 / 275.4 | 3.66 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 256x256; 4 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 5.78 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. Three camera views, each with two frames (GR00T N1.7 temporal input). | T3 · community reported |
| Evo-1 | ONNX (split) | fp16 | 1 | 289.18 / 292.12 | 3.45 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Untrained action head: measures inference cost of the EVO1 architecture only; the author marks it as never to control a robot. Author labels the precision "mixed FP16". | T3 · community reported |
| Evo-1 | TensorRT | fp16 | 2 @640x480 | 332.77 / 333.63 | 3 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 448x448; 32 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 2.76 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| X-VLA | TensorRT | fp16 | 3 @640x480 | 342.59 / 343.47 | 2.92 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations resized by the exported policy to 224x224; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 3.04 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| X-VLA | ONNX (split) | fp16 | 3 | 391.55 / 407.33 | 2.55 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Configured EP priority 12 graphs TensorRT. System RAM 5395 MB in use. | T3 · community reported |
| Evo-1 | ONNX (split) | fp16 | 2 | 414.67 / 424.72 | 2.41 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · tensorrt 10.16.2 (system, via ONNX Runtime TensorRT EP)conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 · onnxruntime-gpu: 1.24 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Author labels the precision "mixed FP16". System RAM 6001 MB in use. | T3 · community reported |
| π0.5 | TensorRT | fp16 | 2 @640x480 | 438.47 / 438.93 | 2.28 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 6.39 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| π0.5 | TensorRT | fp16 | 3 @640x480 | 643.39 / 644.92 | 1.55 Hz | jetpack 7.2.1 · power_mode MAXN_SUPER, clocks pinned with jetson_clocks (GPU 1020 MHz, CPU 1728 MHz) · tensorrt 10.16.2.10conditionsboard: Jetson Orin Nano Engineering Reference Developer Kit Super (8 GB) · l4t: R39.2.1 · os: Ubuntu 24.04.4 LTS · python: 3.12.3 · desktop: running Inference cost only; not task success. 300 s run on synthetic 640x480 observations; 10 denoising steps; latency is runtime-only over a pre-materialized observation ring. Whole-board RAM in use 6.18 GB (unified memory, desktop running). Actions were gated against the stock policy (cosine >= 0.99999) before timing. | T3 · community reported |
| SmolVLA | PyTorch eager | fp32 | 2 | 1167.93 / 1176.65 | 0.86 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · lerobot 0.5.1conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Stock LeRobot SmolVLAPolicy in PyTorch FP32 (LeRobot 0.5.1 env, JetPack-matched torch). RSS peak 3826 MB, system RAM 4126 MB in use. | T3 · community reported |
| X-VLA | PyTorch eager | fp32 | 3 | 2313.5 / 2320.89 | 0.43 Hz | jetpack 7.2 (L4T R39.2.x, per the repo host-setup doc at this commit) · power_mode MAXN_SUPER, pinned clocks · cuda 13.2 · lerobot 0.6.1conditionsboard: Jetson Orin Nano Super 8 GB developer kit · os: Ubuntu 24.04 Inference cost only; not task success. Deterministic synthetic observations, pinned MAXN_SUPER clocks. Stock LeRobot X-VLA policy in PyTorch FP32 (LeRobot 0.6.1 env). At 30 Hz control the 30-step chunk is overrun (author's control-rate fit). System RAM 5450 MB in use. | T3 · community reported |
Sources
- T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
NVIDIA Jetson Orin Nano Super Developer Kit spec table: 67 INT8 TOPS, Ampere GPU with 1024 CUDA cores and 32 Tensor Cores.
“Specifications Jetson Orin Nano Super Developer Kit AI Performance 67 INT8 TOPS GPU NVIDIA Ampere architecture with 1024 CUDA cores and 32 tensor cores”
https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/nano-super-developer-kit/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
Same spec table: 8 GB 128-bit LPDDR5 at 102 GB/s; 7W–25W.
“Memory 8GB 128-bit LPDDR5 102 GB/s Storage Supports SD card slot and external NVMe Power 7W–25W”
https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/nano-super-developer-kit/ - T1 · upstream documentedvendor-docsverified 2026-10-24 (1d ago)
The Super uplift is a software update to the existing Orin Nano developer kit (40 to 67 TOPS, 68 to 102 GB/s).
“NVIDIA's latest software update enhances Jetson Orin Nano's AI performance from 40 to 67 AI TOPs and memory bandwidth from 68 to 102 GB/s”
https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/nano-super-developer-kit/ - T1 · upstream documentedrelease-notesverified 2026-10-24 (1d ago)
NVIDIA JetPack 6.2 page: JetPack 6.2 (Jetson Linux 36.4.3) introduces the high-power Super modes for Orin Nano and Orin NX production modules.
“JetPack 6.2 supports new high-power Super Mode for NVIDIA Jetson Orin Nano and Jetson Orin NX production modules.”
https://developer.nvidia.com/embedded/jetpack-sdk-62 - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)jetson_linux 36.4.3
Jetson Linux r36.4.3 power-mode table for Orin Nano 8GB / 8GB Super: 15W, 7W (non-Super); 15W, 25W, MAXN_SUPER (Super).
“Jetson Orin Nano 8GB Jetson Orin Nano 8GB Super Property Mode Mode 15W* 7W 15W 25W* MAXN_SUPER** Power budget 15W 7W 15W 25W n/a”
https://docs.nvidia.com/jetson/archives/r36.4.3/DeveloperGuide/SD/PlatformPowerAndPerformance/JetsonOrinNanoSeriesJetsonOrinNxSeriesAndJetsonAgxOrinSeries.html - T1 · upstream documentedofficial-docsverified 2026-10-24 (1d ago)jetson_linux 36.4.3
MAXN_SUPER requires flashing with the devkit-super configuration.
“MAXN_SUPER mode is available only when flashing with the jetson-orin-nano-devkit-super configurations.”
https://docs.nvidia.com/jetson/archives/r36.4.3/DeveloperGuide/SD/PlatformPowerAndPerformance/JetsonOrinNanoSeriesJetsonOrinNxSeriesAndJetsonAgxOrinSeries.html