Compare · GPUs & AI chips

Instinct MI300X vs Trainium2

RANKED BY DENSE FP16/BF16 TENSOR TFLOPS PER CHIP #7 VS #12 CHECKED 06 SEPT 2026

Side by side

Verdict

Instinct MI300X ranks #7 of 20 on Dense FP16/BF16 tensor TFLOPS per chip (1.3 PFLOPS); Trainium2 ranks #12 (667 TFLOPS).

Rank 07 of 20 · leads

Instinct MI300X

Dense FP16/BF16 tensor TFLOPS per chip

1.3 PFLOPS

MakerAMD

Date2023

Verified04 Sept 2026

Evidence

AMD Instinct MI300X product page, per-GPU spec: "Peak Half Precision (FP16) Performance 1.3 PFLOPs" / Peak bfloat16 1.3 PFLOPs; structured-sparsity counterparts 2.61 PFLOPs. Launch date on the page: 6 December 2023. 192 GB HBM3. Same dense FP16 figure as MI325X.

Rank 12 of 20

Trainium2

Dense FP16/BF16 tensor TFLOPS per chip

667 TFLOPS

MakerAWS

Date2024

Verified04 Sept 2026

Evidence

AWS Neuron Trainium2 Architecture page, compute table: each Trainium2 chip delivers "667 BF16/FP16/TF32 TFLOPS" dense; sparse counterpart is 2,563 TFLOPS and was not used. 96 GiB device memory. Trn2 instances are generally available (AWS announcement 3 Dec 2024).

Try another pair

More Instinct MI300X 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