DEPLOYDatabase

Chip comparison

Meta MTIA v2 vs NVIDIA GB300 (Blackwell Ultra)

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 GB300 (Blackwell Ultra)
Process nodeTSMC N5TSMC 4NP
TDP90 W1400 W
Memory128 GB LPDDR5288 GB HBM3e
Memory bandwidth205 GB/s8,000 GB/s
FP8 (dense)5,000 TFLOPS
INT8 (dense)708 TOPS
Form factorPCIe (internal Meta)Superchip (Blackwell Ultra + Grace)
Announced2024-04-102025-03-18
Released2024-05-012025-11-01

Robots running Meta MTIA v2

No robots publicly running it yet.

Robots running NVIDIA GB300 (Blackwell Ultra)

No robots publicly running it yet.

Data centers with NVIDIA GB300 (Blackwell Ultra)

Common questions

Meta MTIA v2 vs NVIDIA GB300 (Blackwell Ultra): which has more memory?

NVIDIA GB300 (Blackwell Ultra) carries more HBM (Meta MTIA v2: 128 GB LPDDR5; NVIDIA GB300 (Blackwell Ultra): 288 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 GB300 (Blackwell Ultra): which is more widely used?

Meta MTIA v2: 0 robots and 2 data centers publicly running it. NVIDIA GB300 (Blackwell Ultra): 0 robots and 1 data center. 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 GB300 (Blackwell Ultra) full page.