Compare · GPUs & AI chips

Instinct MI325X vs H100 SXM

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #6 VS #9 CHECKED 06 SEPT 2026

Side by side

Verdict

Instinct MI325X ranks #6 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (1.3 PFLOPS); H100 SXM ranks #9 (0.990 PFLOPS).

Rank 06 of 20 · leads

Instinct MI325X

Dense FP16/BF16 tensor TFLOPS per chip

1.3 PFLOPS

MakerAMD

Date2024

Verified04 Sept 2026

Evidence

AMD Instinct MI325X product page, per-GPU spec: "Peak Half Precision (FP16) Performance 1.3 PFLOPs" and structured-sparsity 2.61 PFLOPs. Launch date on the page: 10 October 2024. 256 GB HBM3E. Tied on this compute metric with MI300X; the MI325X difference is memory.

Rank 09 of 20

H100 SXM

Dense FP16/BF16 tensor TFLOPS per chip

0.990 PFLOPS

MakerNVIDIA

Date2022

Verified04 Sept 2026

Evidence

NVIDIA H100 product page, H100 SXM column: FP16/BF16 Tensor Core 1,979 teraFLOPS. H100 datasheet footnote 2: "With sparsity." Dense is 1,979 / 2 = 989.5 TFLOPS (0.990 PFLOPS). 80 GB HBM3. Tied with H200 SXM on this compute metric.

Try another pair

More Instinct MI325X 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