Compare · GPUs & AI chips

Blackwell Ultra B300 SXM vs TPU v5p

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #4 VS #13 CHECKED 06 SEPT 2026

Side by side

Verdict

Blackwell Ultra B300 SXM ranks #4 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (2.25 PFLOPS); TPU v5p ranks #13 (459 TFLOPS).

Rank 04 of 20 · leads

Blackwell Ultra B300 SXM

Dense FP16/BF16 tensor TFLOPS per chip

2.25 PFLOPS

MakerNVIDIA

Date2025

Verified04 Sept 2026

Evidence

NVIDIA HGX Platform page, HGX B300 row ("8x NVIDIA Blackwell Ultra SXM", shipping now). FP16/BF16 Tensor Core is the same 36 PFLOPS sparse / 18 PFLOPS dense board total as B200, so 2.25 PFLOPS dense per chip. B300's advertised uplift versus B200 is at FP4 and HBM capacity, not at dense FP16/BF16 — so on this metric B200 and B300 are tied.

Rank 13 of 20

TPU v5p

Dense FP16/BF16 tensor TFLOPS per chip

459 TFLOPS

MakerGoogle

Date2023

Verified04 Sept 2026

Evidence

Google Cloud TPU v5p documentation, per-chip specification table: "Peak compute per chip (BF16) (TFLOPs) 459". Same page lists FP8 at 459 TFLOPs. 95 GiB HBM per chip.

Try another pair

More Blackwell Ultra B300 SXM matchups

Source Vendor product pages and official spec documents (AMD Instinct MI355X / MI350X / MI325X / MI300X / MI300A / MI250X / MI250 / MI210; NVIDIA… Last checked 06 Sept 2026

Full GPUs & AI chips ranking Spot an error? Send a tip