H100 NVL vs Radeon RX 9070 XT: Specs
Architecture, compute capability and supported precisions for the H100 NVL and the Radeon RX 9070 XT, 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 | Radeon RX 9070 XT |
|---|---|---|
| VRAM | 94GB HBM3 | 16GB GDDR6 |
| Memory bandwidth | 3.9 TB/s | 640 GB/s |
| Architecture | Hopper | RDNA 4 |
| Compute capability | 9.0 | n/a |
| Precisions in hardware | FP32, FP16, BF16, FP8, INT4 | FP32, FP16, BF16, FP8, INT4 |
| Peak FP16/BF16 tensor TFLOPS | 835.5 TFLOPS | 195 TFLOPS |
| Peak FP8 tensor TFLOPS | 1,670.5 TFLOPS | 389 TFLOPS |
| NVLink / multi-GPU interconnect | NVLink, 600 GB/s | – |
| Max board power (TDP) | 350-400W (configurable) | 304W |
