H100 NVL vs RTX 3090: Specs
Architecture, compute capability and supported precisions for the H100 NVL and the RTX 3090, from vendor datasheets.
No live price to compare
No provider on Aquanode is listing at least one of these two cards right now, so no hourly rate is shown. This page shows live prices as soon as both are listed.
Specs side by side
| Spec | H100 NVL | RTX 3090 |
|---|---|---|
| VRAM | 94GB HBM3 | 24GB GDDR6X |
| Memory bandwidth | 3.9 TB/s | 936 GB/s |
| Architecture | Hopper | Ampere |
| Compute capability | 9.0 | 8.6 |
| Precisions in hardware | FP32, FP16, BF16, FP8, INT4 | FP32, FP16, BF16, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 835.5 TFLOPS | 142 TFLOPS |
| Peak FP8 tensor TFLOPS | 1,670.5 TFLOPS | – |
| NVLink / multi-GPU interconnect | NVLink, 600 GB/s | NVLink, 2-way |
| Max board power (TDP) | 350-400W (configurable) | 350W |
