GB300 NVL72 (per GPU) specs
NVIDIA · Shipping now · first available Aug 2025 (estimated). Dense compute, memory, bandwidth and power from the vendor's documents; each precision stays separate.
All accelerators · Compare with B300 (HGX Blackwell Ultra)
Specifications
| Dense BF16 · FP32 accumulate | 2,500 TFLOPS |
|---|---|
| Dense FP8 · FP32 accumulate | 5,000 TFLOPS |
| Dense FP4 · FP32 accumulate | 15,000 TFLOPS |
| Memory | 279 GB · HBM |
| Memory bandwidth | 8 TB/s |
| Maximum chip power | 1,400 W |
| Interconnect | NVLink 5 · 1.8 TB/s |
| Process node | TSMC 4NPest — estimated / secondary-source figure |
| First availability | Aug 2025est — estimated / secondary-source figure |
| Availability | Shipping |
One of the 72 Blackwell Ultra GPUs in a GB300 NVL72 rack; dense FP4 is 1.5× GB200's, with BF16 and FP8 unchanged. Launch month is an estimate: the first racks shipped in July 2025 and the first cloud instances followed in August.
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 | 1.79 |
| Bandwidth bytes per 1,000 BF16 FLOP | 3.20 |
| $ per dense FP8 PFLOP-hour | No on-demand quote |
| Dense FP8 TFLOPS per watt | 3.57 |
| Bandwidth bytes per 1,000 FP8 FLOP | 1.60 |
| $ 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 . Datasheet's individual-GPU GB300 NVL72 column: FP4 20 | 15 PF sparse | dense; FP8 10 and BF16 5 PF sparse, halved as the footnote directs to 5 and 2.5 PF; 279 GB HBM3E at 8 TB/s; TDP configurable up to 1,400 W. The rack page's totals divided by 72 agree. The process node comes from NVIDIA's Blackwell Ultra technical blog.