Chip comparison
AMD Instinct MI325X vs SambaNova SN40L
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 | SambaNova SN40L |
|---|---|---|
| Process node | TSMC N5 + N6 (chiplet) | TSMC N5 |
| TDP | 1000 W | 700 W |
| Memory | 256 GB HBM3e | 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5) |
| Memory bandwidth | 6,000 GB/s | — |
| FP16 (dense) | 1,307 TFLOPS | 638 TFLOPS |
| BF16 (dense) | 1,307 TFLOPS | — |
| FP8 (dense) | 2,614 TFLOPS | 1,250 TFLOPS |
| INT8 (dense) | 2,614 TOPS | — |
| Form factor | OAM | PCIe (SN40L DataScale system) |
| Announced | 2024-10-10 | 2023-09-19 |
| Released | 2025-01-01 | 2024-01-01 |
Robots running AMD Instinct MI325X
No robots publicly running it yet.
Robots running SambaNova SN40L
No robots publicly running it yet.
Data centers with AMD Instinct MI325X
No data centers publicly running it yet.
Data centers with SambaNova SN40L
No data centers publicly running it yet.
Common questions
AMD Instinct MI325X vs SambaNova SN40L: which is faster for training?
AMD Instinct MI325X has 2.09x the dense FP8 throughput of the other (AMD Instinct MI325X: 2,614 TFLOPS; SambaNova SN40L: 1,250 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 SambaNova SN40L: which has more memory?
SambaNova SN40L carries more HBM (AMD Instinct MI325X: 256 GB HBM3e; SambaNova SN40L: 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
AMD Instinct MI325X vs SambaNova SN40L: which is more power-efficient?
Dense FP8 TFLOPS per watt: AMD Instinct MI325X 2.61 (2,614 ÷ 1000 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). AMD Instinct MI325X wins at the die level; system-level efficiency also depends on cooling and interconnect.
See also: every chip comparison · AMD Instinct MI325X full page · SambaNova SN40L full page.