DEPLOYDatabase

Chip comparison

AWS Inferentia 2 vs NVIDIA L40S

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.

FieldAWS Inferentia 2NVIDIA L40S
Process nodeTSMC N7TSMC 4N
Transistors (B)76.3
TDP250 W350 W
Memory32 GB HBM348 GB GDDR6
Memory bandwidth820 GB/s864 GB/s
FP16 (dense)362 TFLOPS
BF16 (dense)190 TFLOPS362 TFLOPS
FP8 (dense)380 TFLOPS733 TFLOPS
INT8 (dense)733 TOPS
Form factorInf2 EC2 instancePCIe
Announced2022-12-012023-08-08
Released2023-04-01

Robots running AWS Inferentia 2

No robots publicly running it yet.

Robots running NVIDIA L40S

No robots publicly running it yet.

Data centers with AWS Inferentia 2

No data centers publicly running it yet.

Data centers with NVIDIA L40S

No data centers publicly running it yet.

Common questions

AWS Inferentia 2 vs NVIDIA L40S: which is faster for training?

NVIDIA L40S has 1.93x the dense FP8 throughput of the other (AWS Inferentia 2: 380 TFLOPS; NVIDIA L40S: 733 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

AWS Inferentia 2 vs NVIDIA L40S: which has more memory?

NVIDIA L40S carries more HBM (AWS Inferentia 2: 32 GB HBM3; NVIDIA L40S: 48 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

AWS Inferentia 2 vs NVIDIA L40S: which is more power-efficient?

Dense FP8 TFLOPS per watt: AWS Inferentia 2 1.52 (380 ÷ 250 W); NVIDIA L40S 2.09 (733 ÷ 350 W). NVIDIA L40S wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · AWS Inferentia 2 full page · NVIDIA L40S full page.