Chip comparison
Google TPU v5p vs NVIDIA GB200 Grace Blackwell Superchip
Side-by-side specs
Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.
| Field | Google TPU v5p | NVIDIA GB200 Grace Blackwell Superchip |
|---|---|---|
| Process node | — | TSMC 4NP |
| TDP | 300 W | 2700 W |
| Memory | 95 GB HBM2e | 384 GB HBM3e |
| Memory bandwidth | 2,765 GB/s | 16,000 GB/s |
| BF16 (dense) | 459 TFLOPS | — |
| FP8 (dense) | — | 9,000 TFLOPS |
| INT8 (dense) | 918 TOPS | — |
| Form factor | OAM (per-chip in v5p pod) | Superchip (2xB200 + 1xGrace) |
| Announced | 2023-12-06 | 2024-03-18 |
| Released | 2024-01-01 | 2024-12-01 |
Robots running Google TPU v5p
No robots publicly running it yet.
Robots running NVIDIA GB200 Grace Blackwell Superchip
No robots publicly running it yet.
Data centers with Google TPU v5p
Data centers with NVIDIA GB200 Grace Blackwell Superchip
Common questions
Google TPU v5p vs NVIDIA GB200 Grace Blackwell Superchip: which is faster for training?
NVIDIA GB200 Grace Blackwell Superchip has 19.61x the dense FP16/BF16 throughput of the other (Google TPU v5p: 459 TFLOPS; NVIDIA GB200 Grace Blackwell Superchip: 9,000 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
Google TPU v5p vs NVIDIA GB200 Grace Blackwell Superchip: which has more memory?
NVIDIA GB200 Grace Blackwell Superchip carries more HBM (Google TPU v5p: 95 GB HBM2e; NVIDIA GB200 Grace Blackwell Superchip: 384 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
Google TPU v5p vs NVIDIA GB200 Grace Blackwell Superchip: which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Google TPU v5p 1.53 (459 ÷ 300 W); NVIDIA GB200 Grace Blackwell Superchip 3.33 (9,000 ÷ 2700 W). NVIDIA GB200 Grace Blackwell Superchip wins at the die level; system-level efficiency also depends on cooling and interconnect.
Google TPU v5p vs NVIDIA GB200 Grace Blackwell Superchip: which is more widely used?
Google TPU v5p: 0 robots and 1 data center publicly running it. NVIDIA GB200 Grace Blackwell Superchip: 0 robots and 11 data centers. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · Google TPU v5p full page · NVIDIA GB200 Grace Blackwell Superchip full page.