Meta MTIA v1
Meta's first in-house AI accelerator, built for its recommendation workloads on TSMC 7nm, delivers 102.4 TOPS INT8 at just 25 W. Meta now calls it MTIA 100. Sources and verification dates.
Every published figure
Source per value- Owner The company that specified the chip and runs it in its own cloud, data centers or products.
- Meta 1
- Role What the owner says the chip is for: training, inference, both, or a general-purpose server CPU.
- Inference 1
- Foundry The fab that manufactures the die (TSMC, Samsung, SMIC, Intel).
- TSMC 1
- Node Process node as the owner or foundry states it, for example 'TSMC N3' or '7 nm'.
- TSMC 7nm 1
- Memory On-package memory type (HBM2e, HBM3, HBM3E, LPDDR5) or, for CPUs, the memory the socket drives (DDR5).
- LPDDR5 2
- Memory capacity GB On-package memory per chip in GB. Blank for CPUs, whose memory sits off-package.
- 64 2
- Memory bandwidth TB/s Peak memory bandwidth per chip in TB/s, as published.
- 0.176 2
- FP16 TFLOPS Published FP16 throughput per chip or accelerator module in TFLOPS. See the precision note for shared-format figures, sparsity and module scope.
- 51.2 1
- INT8 TOPS Peak INT8 throughput per chip in TOPS, as published. Mostly given for inference chips.
- 102.4 1
- Precision note What the throughput figures mean: dense or sparse, which precision, per chip or per package, and any figure the owner states only in another unit.
- FP16 figure (51.2 TFLOPS). Off-chip memory is LPDDR5, not HBM: 64 GB at 176 GB/s per Meta's 2024 comparison table (the 2023 post says it can scale to 128 GB). 128 MB on-chip SRAM, 800 MHz. 1
- Power W Chip or package power in watts as published (TDP, TBP or typical power; the source says which).
- 25 1
- Status Announced: public roadmap without verified deployment. Sampling: first silicon or limited internal use. Preview: customers can request early access, without a GA claim. Deployed: stated production use or general availability. Discontinued: program stopped.
- Deployed 3
- Announced Year the owner first announced the chip publicly.
- 2,023 1
- How to get it How an outside buyer can use the chip: a named cloud instance or service, a product, or 'Internal only'.
- Internal only 1
Not verified in the sources reviewed: design partner, partner basis, bf16, mxfp8, mxfp4, mx8, mx4, fp8, fp4, largest pod, deployment scale.
Sources
- Meta AI: MTIA v1: Meta's first-generation AI inference accelerator accessed 2026-11-11
- Meta AI: Our next-generation Meta Training and Inference Accelerator accessed 2026-11-11
- Meta AI: MTIA: scaling AI chips for billions accessed 2026-11-11