DEPLOYDatabase

Chip comparison

Meta MTIA v2 vs NVIDIA H100 Tensor Core GPU

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.

FieldMeta MTIA v2NVIDIA H100 Tensor Core GPU
Process nodeTSMC N5TSMC 4N
Transistors (B)80
Die size814 mm²
TDP90 W700 W
Memory128 GB LPDDR580 GB HBM3
Memory bandwidth205 GB/s3,350 GB/s
FP16 (dense)989 TFLOPS
BF16 (dense)989 TFLOPS
FP8 (dense)1,979 TFLOPS
INT8 (dense)708 TOPS1,979 TOPS
Launch price (list)$30,000
Form factorPCIe (internal Meta)SXM5
Announced2024-04-102022-03-22
Released2024-05-012022-10-13

Robots running Meta MTIA v2

No robots publicly running it yet.

Robots running NVIDIA H100 Tensor Core GPU

No robots publicly running it yet.

Common questions

Meta MTIA v2 vs NVIDIA H100 Tensor Core GPU: which has more memory?

Meta MTIA v2 carries more HBM (Meta MTIA v2: 128 GB LPDDR5; NVIDIA H100 Tensor Core GPU: 80 GB HBM3). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Meta MTIA v2 vs NVIDIA H100 Tensor Core GPU: which is more widely used?

Meta MTIA v2: 0 robots and 2 data centers publicly running it. NVIDIA H100 Tensor Core GPU: 0 robots and 7 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 H100 Tensor Core GPU full page.