DEPLOYDatabase

Chip comparison

Google TPU v5p 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.

FieldGoogle TPU v5pNVIDIA GB300 (Blackwell Ultra)
Process nodeTSMC 4NP
TDP300 W1400 W
Memory95 GB HBM2e288 GB HBM3e
Memory bandwidth2,765 GB/s8,000 GB/s
BF16 (dense)459 TFLOPS
FP8 (dense)5,000 TFLOPS
INT8 (dense)918 TOPS
Form factorOAM (per-chip in v5p pod)Superchip (Blackwell Ultra + Grace)
Announced2023-12-062025-03-18
Released2024-01-012025-11-01

Robots running Google TPU v5p

No robots publicly running it yet.

Robots running NVIDIA GB300 (Blackwell Ultra)

No robots publicly running it yet.

Data centers with Google TPU v5p

Data centers with NVIDIA GB300 (Blackwell Ultra)

Common questions

Google TPU v5p vs NVIDIA GB300 (Blackwell Ultra): which is faster for training?

NVIDIA GB300 (Blackwell Ultra) has 10.89x the dense FP16/BF16 throughput of the other (Google TPU v5p: 459 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 v5p vs NVIDIA GB300 (Blackwell Ultra): which has more memory?

NVIDIA GB300 (Blackwell Ultra) carries more HBM (Google TPU v5p: 95 GB HBM2e; 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 v5p vs NVIDIA GB300 (Blackwell Ultra): which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v5p 1.53 (459 ÷ 300 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.

See also: every chip comparison · Google TPU v5p full page · NVIDIA GB300 (Blackwell Ultra) full page.