Compare · GPUs & AI chips
Instinct MI350X vs A100 SXM 80GB
RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP
#2 VS #17
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); A100 SXM 80GB ranks #17 (312 TFLOPS).
Rank 02 of 20 · leads
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 17 of 20
Dense FP16/BF16 tensor TFLOPS per chip
312 TFLOPS
MakerNVIDIA
Date2020
Verified04 Sept 2026
Evidence
NVIDIA A100 product page, A100 80GB SXM column: FP16 Tensor Core 312 TFLOPS | 624 TFLOPS* and BFLOAT16 Tensor Core 312 TFLOPS | 624 TFLOPS*. Asterisk is "With sparsity". Dense figure used here is 312 TFLOPS. 80 GB HBM2e.Try another pair
More Instinct MI350X matchups
- Instinct MI350X vs Instinct MI355X
- Instinct MI350X vs Blackwell B200 SXM
- Instinct MI350X vs Blackwell Ultra B300 SXM
- Instinct MI350X vs Gaudi 3
- Instinct MI350X vs Instinct MI325X
- Instinct MI350X vs Instinct MI300X
- Instinct MI350X vs H200 SXM
- Instinct MI350X vs H100 SXM
- Instinct MI350X vs Instinct MI300A
- Instinct MI350X vs TPU v6e (Trillium)
- Instinct MI350X vs Trainium2
- Instinct MI350X vs TPU v5p
Source Vendor product pages and official spec documents (AMD Instinct MI355X / MI350X / MI325X / MI300X / MI300A / MI250X / MI250 / MI210; NVIDIA…
Last checked 06 Sept 2026