Chip comparison
Google TPU v4 vs NVIDIA GB300 (Blackwell Ultra)
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 v4 | NVIDIA GB300 (Blackwell Ultra) |
|---|---|---|
| Process node | TSMC N7 | TSMC 4NP |
| TDP | 192 W | 1400 W |
| Memory | 32 GB HBM2 | 288 GB HBM3e |
| Memory bandwidth | 1,200 GB/s | 8,000 GB/s |
| BF16 (dense) | 275 TFLOPS | — |
| FP8 (dense) | — | 5,000 TFLOPS |
| INT8 (dense) | 275 TOPS | — |
| Form factor | OAM (per-chip in v4 pod) | Superchip (Blackwell Ultra + Grace) |
| Announced | 2021-05-18 | 2025-03-18 |
| Released | 2022-05-01 | 2025-11-01 |
Robots running Google TPU v4
No robots publicly running it yet.
Robots running NVIDIA GB300 (Blackwell Ultra)
No robots publicly running it yet.
Data centers with Google TPU v4
Data centers with NVIDIA GB300 (Blackwell Ultra)
Common questions
Google TPU v4 vs NVIDIA GB300 (Blackwell Ultra): which is faster for training?
NVIDIA GB300 (Blackwell Ultra) has 18.18x the dense FP16/BF16 throughput of the other (Google TPU v4: 275 TFLOPS; NVIDIA GB300 (Blackwell Ultra): 5,000 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
Google TPU v4 vs NVIDIA GB300 (Blackwell Ultra): which has more memory?
NVIDIA GB300 (Blackwell Ultra) carries more HBM (Google TPU v4: 32 GB HBM2; NVIDIA GB300 (Blackwell Ultra): 288 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
Google TPU v4 vs NVIDIA GB300 (Blackwell Ultra): which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: Google TPU v4 1.43 (275 ÷ 192 W); NVIDIA GB300 (Blackwell Ultra) 3.57 (5,000 ÷ 1400 W). NVIDIA GB300 (Blackwell Ultra) wins at the die level; system-level efficiency also depends on cooling and interconnect.
Google TPU v4 vs NVIDIA GB300 (Blackwell Ultra): which is more widely used?
Google TPU v4: 0 robots and 2 data centers publicly running it. NVIDIA GB300 (Blackwell Ultra): 0 robots and 1 data center. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · Google TPU v4 full page · NVIDIA GB300 (Blackwell Ultra) full page.