Chip comparison
Google TPU v5p vs NVIDIA B100 (Blackwell)
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 B100 (Blackwell) |
|---|---|---|
| Process node | — | TSMC 4NP |
| TDP | 300 W | 700 W |
| Memory | 95 GB HBM2e | 192 GB HBM3e |
| Memory bandwidth | 2,765 GB/s | 8,000 GB/s |
| FP16 (dense) | — | 1,750 TFLOPS |
| BF16 (dense) | 459 TFLOPS | 1,750 TFLOPS |
| FP8 (dense) | — | 3,500 TFLOPS |
| INT8 (dense) | 918 TOPS | — |
| Form factor | OAM (per-chip in v5p pod) | SXM6 (700 W envelope) |
| Announced | 2023-12-06 | 2024-03-18 |
| Released | 2024-01-01 | 2024-11-01 |
Robots running Google TPU v5p
No robots publicly running it yet.
Robots running NVIDIA B100 (Blackwell)
No robots publicly running it yet.
Data centers with Google TPU v5p
Data centers with NVIDIA B100 (Blackwell)
No data centers publicly running it yet.
Common questions
Google TPU v5p vs NVIDIA B100 (Blackwell): which is faster for training?
NVIDIA B100 (Blackwell) has 7.63x the dense FP16/BF16 throughput of the other (Google TPU v5p: 459 TFLOPS; NVIDIA B100 (Blackwell): 3,500 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 B100 (Blackwell): which has more memory?
NVIDIA B100 (Blackwell) carries more HBM (Google TPU v5p: 95 GB HBM2e; NVIDIA B100 (Blackwell): 192 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 B100 (Blackwell): which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Google TPU v5p 1.53 (459 ÷ 300 W); NVIDIA B100 (Blackwell) 5.00 (3,500 ÷ 700 W). NVIDIA B100 (Blackwell) wins at the die level; system-level efficiency also depends on cooling and interconnect.
Google TPU v5p vs NVIDIA B100 (Blackwell): which is more widely used?
Google TPU v5p: 0 robots and 1 data center publicly running it. NVIDIA B100 (Blackwell): 0 robots and 0 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 B100 (Blackwell) full page.