DEPLOYDatabase

Chip comparison

NVIDIA L40S vs SambaNova SN40L

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.

FieldNVIDIA L40SSambaNova SN40L
Process nodeTSMC 4NTSMC N5
Transistors (B)76.3
TDP350 W700 W
Memory48 GB GDDR61500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)
Memory bandwidth864 GB/s
FP16 (dense)362 TFLOPS638 TFLOPS
BF16 (dense)362 TFLOPS
FP8 (dense)733 TFLOPS1,250 TFLOPS
INT8 (dense)733 TOPS
Form factorPCIePCIe (SN40L DataScale system)
Announced2023-08-082023-09-19
Released2024-01-01

Robots running NVIDIA L40S

No robots publicly running it yet.

Robots running SambaNova SN40L

No robots publicly running it yet.

Data centers with NVIDIA L40S

No data centers publicly running it yet.

Data centers with SambaNova SN40L

No data centers publicly running it yet.

Common questions

NVIDIA L40S vs SambaNova SN40L: which is faster for training?

SambaNova SN40L has 1.71x the dense FP8 throughput of the other (NVIDIA L40S: 733 TFLOPS; SambaNova SN40L: 1,250 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

NVIDIA L40S vs SambaNova SN40L: which has more memory?

SambaNova SN40L carries more HBM (NVIDIA L40S: 48 GB GDDR6; SambaNova SN40L: 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

NVIDIA L40S vs SambaNova SN40L: which is more power-efficient?

Dense FP8 TFLOPS per watt: NVIDIA L40S 2.09 (733 ÷ 350 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). NVIDIA L40S wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · NVIDIA L40S full page · SambaNova SN40L full page.