Chip comparison
AMD Instinct MI325X vs NVIDIA H200 Tensor Core GPU
Side-by-side specs
Straight from each vendor's datasheet. Winner in bold: higher throughput, memory, or transistor count; lower power draw or price. Sparse (2:4) throughput roughly doubles the FP8/INT8 numbers shown.
| Field | AMD Instinct MI325X | NVIDIA H200 Tensor Core GPU |
|---|---|---|
| Process node | TSMC N5 + N6 (chiplet) | TSMC 4N |
| Transistors (B) | — | 80 |
| Die size | — | 814 mm² |
| TDP | 1000 W | 700 W |
| Memory | 256 GB HBM3e | 141 GB HBM3e |
| Memory bandwidth | 6,000 GB/s | 4,800 GB/s |
| FP16 (dense) | 1,307 TFLOPS | 989 TFLOPS |
| BF16 (dense) | 1,307 TFLOPS | 989 TFLOPS |
| FP8 (dense) | 2,614 TFLOPS | 1,979 TFLOPS |
| INT8 (dense) | 2,614 TOPS | 1,979 TOPS |
| Form factor | OAM | SXM5 |
| Announced | 2024-10-10 | 2023-11-13 |
| Released | 2025-01-01 | 2024-03-01 |
Robots running AMD Instinct MI325X
No robots publicly running it yet.
Robots running NVIDIA H200 Tensor Core GPU
No robots publicly running it yet.
Data centers with AMD Instinct MI325X
No data centers publicly running it yet.
Data centers with NVIDIA H200 Tensor Core GPU
Common questions
AMD Instinct MI325X vs NVIDIA H200 Tensor Core GPU: which is faster for training?
AMD Instinct MI325X has 1.32x the dense FP8 throughput of the other (AMD Instinct MI325X: 2,614 TFLOPS; NVIDIA H200 Tensor Core GPU: 1,979 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
AMD Instinct MI325X vs NVIDIA H200 Tensor Core GPU: which has more memory?
AMD Instinct MI325X carries more HBM (AMD Instinct MI325X: 256 GB HBM3e; NVIDIA H200 Tensor Core GPU: 141 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
AMD Instinct MI325X vs NVIDIA H200 Tensor Core GPU: which is more power-efficient?
Dense FP8 TFLOPS per watt: AMD Instinct MI325X 2.61 (2,614 ÷ 1000 W); NVIDIA H200 Tensor Core GPU 2.83 (1,979 ÷ 700 W). NVIDIA H200 Tensor Core GPU wins at the die level; system-level efficiency also depends on cooling and interconnect.
AMD Instinct MI325X vs NVIDIA H200 Tensor Core GPU: which is more widely used?
AMD Instinct MI325X: 0 robots and 0 data centers publicly running it. NVIDIA H200 Tensor Core GPU: 0 robots and 4 data centers. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · AMD Instinct MI325X full page · NVIDIA H200 Tensor Core GPU full page.