Chip comparison
Meta MTIA v2 vs NVIDIA B200 (Blackwell)
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 | NVIDIA B200 (Blackwell) |
|---|---|---|
| Process node | TSMC N5 | TSMC 4NP |
| Transistors (B) | — | 208 |
| TDP | 90 W | 1000 W |
| Memory | 128 GB LPDDR5 | 192 GB HBM3e |
| Memory bandwidth | 205 GB/s | 8,000 GB/s |
| FP16 (dense) | — | 2,250 TFLOPS |
| BF16 (dense) | — | 2,250 TFLOPS |
| FP8 (dense) | — | 4,500 TFLOPS |
| INT8 (dense) | 708 TOPS | 4,500 TOPS |
| Form factor | PCIe (internal Meta) | SXM6 |
| Announced | 2024-04-10 | 2024-03-18 |
| Released | 2024-05-01 | 2024-11-01 |
Robots running Meta MTIA v2
No robots publicly running it yet.
Robots running NVIDIA B200 (Blackwell)
No robots publicly running it yet.
Data centers with Meta MTIA v2
Data centers with NVIDIA B200 (Blackwell)
Common questions
Meta MTIA v2 vs NVIDIA B200 (Blackwell): which has more memory?
NVIDIA B200 (Blackwell) carries more HBM (Meta MTIA v2: 128 GB LPDDR5; NVIDIA B200 (Blackwell): 192 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.
Meta MTIA v2 vs NVIDIA B200 (Blackwell): which is more widely used?
Meta MTIA v2: 0 robots and 2 data centers publicly running it. NVIDIA B200 (Blackwell): 0 robots and 3 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 · NVIDIA B200 (Blackwell) full page.