Space Computing Energy Tech Transport Science Dev Loyalty ↗ ◐ Dark mode ◎ Enable Alerts
Compare · GPUs & AI chips

Blackwell Ultra B300 SXM vs Instinct MI250X

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #4 VS #15 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); Instinct MI250X ranks #15 (383 TFLOPS).

Rank 04 of 20 · leads
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 15 of 20
Dense FP16/BF16 tensor TFLOPS per chip
383 TFLOPS
MakerAMD
Date2021
Verified04 Sept 2026
Evidence
AMD Instinct MI250X product page: "Peak Half Precision (FP16) Performance 383 TFLOPs" and "Peak bfloat16 383 TFLOPs". Launch date on the page: 8 November 2021. 128 GB HBM2e. No structured-sparsity counterpart is published for MI200-series.
Try another pair
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