NVIDIA H100 PCIe 80GB
Performance
Peak theoretical throughput by precision type
The H100 PCIe 80GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Hopper
Form Factor
PCIe
Launch Year
2022
Process Node
4nm
Memory
80 GB
Bandwidth
2,000 GB/s
TDP
350 W
Max Power
~402 W
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| VRAM | 80 GB |
| Bandwidth | 2.0 TB/s |
| Power & Thermal | |
| TDP | 350 W |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | PCIe |
| Architecture | Hopper |
| Launch Year | 2022 |
Datasheet & Resources
Flopper Datasheet
NVIDIA H100 PCIe 80GB specifications, generated from our database. Printable.
Vendor product page
NVIDIA documentation for the H100 PCIe 80GB
NVIDIA H100 Tensor Core GPU
NVIDIA · 2022-03-22
NVIDIA Developer Documentation
Technical specs, programming guides
Data Provenance
Every figure traced to a source
Primary Source
- Document
- NVIDIA H100 Tensor Core GPU
- Publisher
- NVIDIA
- Published
- 2022-03-22
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Precisions tracked
- 7
- Normalization
- All values in TFLOPS
Rent this GPU
$1.99 / GPU-hr
Lowest of 4 live listings across 2 providers· median $2.25
Price history and every provider on the pricing page. Some links are affiliate links.
Similar GPUs
Frequently Asked Questions
How many TFLOPS does the NVIDIA H100 have?
The NVIDIA H100 delivers 51 TFLOPS for FP32 operations, 756.5 TFLOPS for FP16, and 1513 TFLOPS for FP8 precision.
What is the power consumption of the NVIDIA H100?
The NVIDIA H100 has a TDP (Thermal Design Power) rating of 350 watts.
How much memory does the NVIDIA H100 have?
The NVIDIA H100 is equipped with 80 GB of VRAM with 2000 GB/s memory bandwidth.
What architecture is the NVIDIA H100 based on?
The NVIDIA H100 is based on the Hopper architecture, launched in 2022.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.