Jetson Thor — specs & cloud pricing
The Jetson Thor is a edge / robotics accelerator from NVIDIA. Live specs from the Mintok silicon catalog.
Specifications
- Vendor
- NVIDIA
- Class
- Edge / robotics accelerator
- Architecture
- Blackwell (edge)
- BF16 throughput
- 250 TFLOPS
- On-package memory
- 128 GB LPDDR5X
- Memory bandwidth
- 273 GB/s
- TDP
- 130 W
- Form factor
- SOC_EMBEDDED
- Product lifecycle
- 8 yr
More NVIDIA silicon
- GB300 NVL725,000 TFLOPS · 288GB
- Rubin Ultra VR3005,000 TFLOPS · 1,024GB
- B200 SXM4,500 TFLOPS · 192GB
- Rubin VR2002,500 TFLOPS · 288GB
- NVIDIA B2002,250 TFLOPS · 192GB
- H100 SXM1,979 TFLOPS · 80GB
FAQ
How much memory does the Jetson Thor have?
The Jetson Thor has 128 GB of LPDDR5X memory at 273 GB/s bandwidth.
What is the Jetson Thor's BF16 compute throughput?
The Jetson Thor delivers 250 BF16 TFLOPS at a 130 W TDP.
Is the Jetson Thor a datacenter or edge accelerator?
The Jetson Thor is a edge / robotics accelerator (130 W TDP).
Cost this chip in a fleet
Size a deployment on the Jetson Thor, or see the full priced rack BOM it sits in.
Specs and modeled rates maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.