DEPLOYDatabase

Chip comparison

NVIDIA Jetson AGX Orin vs NVIDIA Jetson AGX Thor

Side-by-side specs

Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.

FieldNVIDIA Jetson AGX OrinNVIDIA Jetson AGX Thor
Process nodeSamsung 8NTSMC 4NP
TDP60 W130 W
Memory64 GB LPDDR5128 GB LPDDR5X
Memory bandwidth204.8 GB/s273 GB/s
FP8 (dense)2,070 TFLOPS
INT8 (dense)275 TOPS2,070 TOPS
Form factorModule (AGX Orin 64GB)Module (AGX Thor)
Announced2022-03-222024-03-18
Released2022-07-012025-08-01

Robots running NVIDIA Jetson AGX Thor

Data centers with NVIDIA Jetson AGX Orin

No data centers publicly running it yet.

Data centers with NVIDIA Jetson AGX Thor

No data centers publicly running it yet.

Common questions

NVIDIA Jetson AGX Orin vs NVIDIA Jetson AGX Thor: which has more memory?

NVIDIA Jetson AGX Thor carries more HBM (NVIDIA Jetson AGX Orin: 64 GB LPDDR5; NVIDIA Jetson AGX Thor: 128 GB LPDDR5X). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

NVIDIA Jetson AGX Orin vs NVIDIA Jetson AGX Thor: which is more widely used?

NVIDIA Jetson AGX Orin: 9 robots and 0 data centers publicly running it. NVIDIA Jetson AGX Thor: 11 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · NVIDIA Jetson AGX Orin full page · NVIDIA Jetson AGX Thor full page.