A100 SXM — specs & cloud pricing
The A100 SXM is a datacenter accelerator from NVIDIA. Live specs and modeled cloud $/hr from the Mintok silicon catalog.
Cloud rate
$3.50per chip-hour (modeled)
Specifications
- Vendor
- NVIDIA
- Class
- Datacenter accelerator
- Architecture
- Ampere
- BF16 throughput
- 312 TFLOPS
- On-package memory
- 80 GB
- Memory bandwidth
- 2,000 GB/s
- TDP
- 400 W
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 does the A100 SXM cost per hour in the cloud?
The A100 SXM rents for about $3.50 per chip-hour on cloud providers (modeled from public rates). Own-vs-rent economics — capex, lease and TCO — are in the Mintok sizing report and rack teardowns.
How much memory does the A100 SXM have?
The A100 SXM has 80 GB of on-package memory at 2,000 GB/s bandwidth.
What is the A100 SXM's BF16 compute throughput?
The A100 SXM delivers 312 BF16 TFLOPS at a 400 W TDP.
Is the A100 SXM a datacenter or edge accelerator?
The A100 SXM is a datacenter accelerator (400 W TDP).
Cost this chip in a fleet
Size a deployment on the A100 SXM, 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.