Chip comparison
AMD Instinct MI350 series vs Cerebras WSE-3 (Wafer-Scale Engine 3)
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 MI350 series | Cerebras WSE-3 (Wafer-Scale Engine 3) |
|---|---|---|
| Process node | TSMC N3 (chiplet) | TSMC N5 |
| Transistors (B) | — | 4000 |
| Die size | — | 46225 mm² |
| TDP | 1000 W | 23000 W |
| Memory | 288 GB HBM3e | 44 GB on-die SRAM |
| Memory bandwidth | 8,000 GB/s | 21,000,000 GB/s |
| FP16 (dense) | 2,300 TFLOPS | 62,500 TFLOPS |
| BF16 (dense) | 2,300 TFLOPS | — |
| FP8 (dense) | 4,600 TFLOPS | — |
| INT8 (dense) | 4,600 TOPS | — |
| Form factor | OAM | wafer-scale (single-wafer system) |
| Announced | 2025-06-12 | 2024-03-13 |
| Released | 2025-10-01 | 2024-04-01 |
Robots running AMD Instinct MI350 series
No robots publicly running it yet.
Robots running Cerebras WSE-3 (Wafer-Scale Engine 3)
No robots publicly running it yet.
Data centers with AMD Instinct MI350 series
Data centers with Cerebras WSE-3 (Wafer-Scale Engine 3)
No data centers publicly running it yet.
Common questions
AMD Instinct MI350 series vs Cerebras WSE-3 (Wafer-Scale Engine 3): which is faster for training?
Cerebras WSE-3 (Wafer-Scale Engine 3) has 13.59x the dense FP16/BF16 throughput of the other (AMD Instinct MI350 series: 4,600 TFLOPS; Cerebras WSE-3 (Wafer-Scale Engine 3): 62,500 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.
AMD Instinct MI350 series vs Cerebras WSE-3 (Wafer-Scale Engine 3): which has more memory?
AMD Instinct MI350 series carries more HBM (AMD Instinct MI350 series: 288 GB HBM3e; Cerebras WSE-3 (Wafer-Scale Engine 3): 44 GB on-die SRAM). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
AMD Instinct MI350 series vs Cerebras WSE-3 (Wafer-Scale Engine 3): which is more power-efficient?
Dense FP16/BF16 TFLOPS per watt: AMD Instinct MI350 series 4.60 (4,600 ÷ 1000 W); Cerebras WSE-3 (Wafer-Scale Engine 3) 2.72 (62,500 ÷ 23000 W). AMD Instinct MI350 series wins at the die level; system-level efficiency also depends on cooling and interconnect.
AMD Instinct MI350 series vs Cerebras WSE-3 (Wafer-Scale Engine 3): which is more widely used?
AMD Instinct MI350 series: 0 robots and 1 data center publicly running it. Cerebras WSE-3 (Wafer-Scale Engine 3): 0 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.
See also: every chip comparison · AMD Instinct MI350 series full page · Cerebras WSE-3 (Wafer-Scale Engine 3) full page.