Chip comparison
Meta MTIA v2 vs Tesla Dojo D1
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 | Meta MTIA v2 | Tesla Dojo D1 |
|---|---|---|
| Process node | TSMC N5 | TSMC N7 |
| Transistors (B) | — | 50 |
| Die size | — | 645 mm² |
| TDP | 90 W | 400 W |
| Memory | 128 GB LPDDR5 | — |
| Memory bandwidth | 205 GB/s | — |
| BF16 (dense) | — | 362 TFLOPS |
| FP8 (dense) | — | 362 TFLOPS |
| INT8 (dense) | 708 TOPS | — |
| Form factor | PCIe (internal Meta) | Training tile (25 D1 chips per tile) |
| Announced | 2024-04-10 | 2021-08-19 |
| Released | 2024-05-01 | 2023-07-01 |
Robots running Meta MTIA v2
No robots publicly running it yet.
Robots running Tesla Dojo D1
No robots publicly running it yet.
Data centers with Meta MTIA v2
Data centers with Tesla Dojo D1
No data centers publicly running it yet.
Common questions
Meta MTIA v2 vs Tesla Dojo D1: which is more widely used?
Meta MTIA v2: 0 robots and 2 data centers publicly running it. Tesla Dojo D1: 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 · Meta MTIA v2 full page · Tesla Dojo D1 full page.