Compare · GPUs & AI chips

Instinct MI350X vs Blackwell B200 SXM

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #2 VS #3 CHECKED 06 SEPT 2026

Side by side

Verdict

Instinct MI350X ranks #2 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (2.3 PFLOPS); Blackwell B200 SXM ranks #3 (2.25 PFLOPS).

Rank 02 of 20 · leads

Instinct MI350X

Dense FP16/BF16 tensor TFLOPS per chip

2.3 PFLOPS

MakerAMD

Date2025

Verified04 Sept 2026

Evidence

AMD Instinct MI350X product page, per-GPU spec: "Peak Half Precision Matrix (FP16) Performance 2.3 PFLOPs" / "Peak bfloat16 (BF16) Matrix Performance 2.3 PFLOPs". Structured-sparsity counterparts are 4.6 PFLOPs and were not used. Launch date on the page: 12 June 2025. 288 GB HBM3E.

Rank 03 of 20

Blackwell B200 SXM

Dense FP16/BF16 tensor TFLOPS per chip

2.25 PFLOPS

MakerNVIDIA

Date2025

Verified04 Sept 2026

Evidence

NVIDIA HGX Platform page, HGX B200 row ("8x NVIDIA Blackwell SXM", footnote 4: "HGX B300 and HGX B200 shipping now"). FP16/BF16 Tensor Core is listed as 36 PFLOPS for the 8-GPU board. Footnote 2: dense is half the sparse spec. Dense board total is therefore 18 PFLOPS; per chip 18 / 8 = 2.25 PFLOPS. Total memory 1.4 TB => 180 GB HBM3E per SXM.

Try another pair

More Instinct MI350X 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