Chip comparison
AMD Instinct MI250X vs Google TPU v7 (Ironwood)
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 MI250X | Google TPU v7 (Ironwood) |
|---|---|---|
| Process node | TSMC N6 | — |
| TDP | 560 W | 700 W |
| Memory | 128 GB HBM2e | 192 GB HBM3e |
| Memory bandwidth | 3,200 GB/s | 7,400 GB/s |
| FP16 (dense) | 383 TFLOPS | — |
| BF16 (dense) | 383 TFLOPS | 4,614 TFLOPS |
| FP8 (dense) | — | 9,228 TFLOPS |
| INT8 (dense) | 383 TOPS | — |
| Form factor | OAM | OAM (Ironwood pod, up to 9,216 chips) |
| Announced | 2021-11-08 | 2025-04-09 |
| Released | 2022-06-01 | 2025-12-01 |
Robots running AMD Instinct MI250X
No robots publicly running it yet.
Robots running Google TPU v7 (Ironwood)
No robots publicly running it yet.
Data centers with AMD Instinct MI250X
No data centers publicly running it yet.
Data centers with Google TPU v7 (Ironwood)
No data centers publicly running it yet.
Common questions
AMD Instinct MI250X vs Google TPU v7 (Ironwood): which is faster for training?
Google TPU v7 (Ironwood) has 24.09x the dense FP16/BF16 throughput of the other (AMD Instinct MI250X: 383 TFLOPS; Google TPU v7 (Ironwood): 9,228 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
AMD Instinct MI250X vs Google TPU v7 (Ironwood): which has more memory?
Google TPU v7 (Ironwood) carries more HBM (AMD Instinct MI250X: 128 GB HBM2e; Google TPU v7 (Ironwood): 192 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
AMD Instinct MI250X vs Google TPU v7 (Ironwood): which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: AMD Instinct MI250X 0.68 (383 ÷ 560 W); Google TPU v7 (Ironwood) 13.18 (9,228 ÷ 700 W). Google TPU v7 (Ironwood) wins at the die level; system-level efficiency also depends on cooling and interconnect.
See also: every chip comparison · AMD Instinct MI250X full page · Google TPU v7 (Ironwood) full page.