OwnAI Compute
Book a call Sign in
Hardware platform

NVIDIA Jetson, module by module

Manufacturer specifications for every platform we build on. Peak TOPS is theoretical; open a platform to see measured LLM throughput where we have it.

7 of 7 platforms
CPU
GPU
Power
Stock
Jetson Orin Nano 4GB6-core Arm Cortex-A78AE, 1.5 MB L2 + 4 MB L3512 CUDA · 16 Tensor · NVIDIA Ampere architecture34 TOPS
INT8, sparse (Super mode)
4517–25 WIn stock
Jetson Orin Nano 8GB6-core Arm Cortex-A78AE, 1.5 MB L2 + 4 MB L31024 CUDA · 32 Tensor · NVIDIA Ampere architecture67 TOPS
INT8, sparse (Super mode)
81027–25 WIn stock
Jetson Orin NX 8GB6-core Arm Cortex-A78AE, 1.5 MB L2 + 4 MB L31024 CUDA · 32 Tensor · NVIDIA Ampere architecture117 TOPS
INT8, sparse (Super mode)
810210–40 WIn stock
Jetson Orin NX 16GB8-core Arm Cortex-A78AE, 2 MB L2 + 4 MB L31024 CUDA · 32 Tensor · NVIDIA Ampere architecture157 TOPS
INT8, sparse (Super mode)
1610210–40 WIn stock
Jetson AGX Orin 32GB8-core Arm Cortex-A78AE, 2 MB L2 + 4 MB L31792 CUDA · 56 Tensor · NVIDIA Ampere architecture200 TOPS
INT8, sparse
32204.815–40 WIn stock
7 items

Rejoining the server...

Rejoin failed... trying again in seconds.

Failed to rejoin.
Please retry or reload the page.

The session has been paused by the server.

Failed to resume the session.
Please retry or reload the page.