NVIDIA H100 — specs & cloud pricing
The NVIDIA H100 is a datacenter accelerator from NVIDIA. Live specs from the Mintok silicon catalog.
Specifications
- Vendor
- NVIDIA
- Class
- Datacenter accelerator
- Architecture
- Hopper
- BF16 throughput
- 1,979 TFLOPS
- On-package memory
- 80 GB
- Memory bandwidth
- 3,350 GB/s
- TDP
- 700 W
- Interconnect
- NVLink 4
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 NVIDIA H100 have?
The NVIDIA H100 has 80 GB of on-package memory at 3,350 GB/s bandwidth.
What is the NVIDIA H100's BF16 compute throughput?
The NVIDIA H100 delivers 1,979 BF16 TFLOPS at a 700 W TDP.
Is the NVIDIA H100 a datacenter or edge accelerator?
The NVIDIA H100 is a datacenter accelerator (700 W TDP).
Cost this chip in a fleet
Size a deployment on the NVIDIA H100, 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.