H100 NVL specs
NVIDIA · Shipping now · first available Mar 2024 (estimated). Dense compute, memory, bandwidth and power from the vendor's documents; each precision stays separate.
All accelerators · Compare with H200 SXM
Specifications
| Dense BF16 · FP32 accumulate | 835.5 TFLOPS |
|---|---|
| Dense FP8 · FP32 accumulate | 1,670.5 TFLOPS |
| Dense FP4 · FP32 accumulate | Not published |
| Memory | 94 GB · HBM |
| Memory bandwidth | 3.9 TB/s |
| Maximum chip power | 400 W |
| Interconnect | NVLink bridge · 600 GB/s |
| First availability | Mar 2024est — estimated / secondary-source figure |
| Availability | Shipping |
Dual-slot PCIe H100 with 94 GB of HBM3, sold in NVLink-bridged pairs. Launch month is an estimate: the first general availability found is Azure's NC H100 v5 in March 2024.
Dense tensor rates with FP32 accumulation, never sparse or FP16-accumulate headline figures. Memory is in decimal GB. The est marker flags a value its vendor-document review did not confirm.
Rent it
No tracked rental quote. The site tracks providers' published list prices; this part may still be rentable under terms it does not record.
Value ratios
| $ per dense BF16 PFLOP-hour | No on-demand quote |
|---|---|
| Dense BF16 TFLOPS per watt | 2.09 |
| Bandwidth bytes per 1,000 BF16 FLOP | 4.67 |
| $ per dense FP8 PFLOP-hour | No on-demand quote |
| Dense FP8 TFLOPS per watt | 4.18 |
| Bandwidth bytes per 1,000 FP8 FLOP | 2.33 |
| $ per GB of memory per hour | No on-demand quote |
Prices divide the cheapest on-demand list price; theoretical ratios do not measure application speed.
Sources
Specifications reviewed . NVL column: sparse 1,671 BF16 and 3,341 FP8 TFLOPS halved; 94 GB HBM3 at 3.9 TB/s (3,938 GB/s in the brief), 400 W maximum by default, NVLink bridge at 600 GB/s. Neither document states a process node.