DEPLOYDatabase

Chip comparison

Google TPU v5p 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.

FieldGoogle TPU v5pSambaNova SN40L
Process nodeTSMC N5
TDP300 W700 W
Memory95 GB HBM2e1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)
Memory bandwidth2,765 GB/s
FP16 (dense)638 TFLOPS
BF16 (dense)459 TFLOPS
FP8 (dense)1,250 TFLOPS
INT8 (dense)918 TOPS
Form factorOAM (per-chip in v5p pod)PCIe (SN40L DataScale system)
Announced2023-12-062023-09-19
Released2024-01-012024-01-01

Robots running Google TPU v5p

No robots publicly running it yet.

Robots running SambaNova SN40L

No robots publicly running it yet.

Data centers with Google TPU v5p

Data centers with SambaNova SN40L

No data centers publicly running it yet.

Common questions

Google TPU v5p vs SambaNova SN40L: which is faster for training?

SambaNova SN40L has 2.72x the dense FP16/BF16 throughput of the other (Google TPU v5p: 459 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.

Google TPU v5p vs SambaNova SN40L: which has more memory?

SambaNova SN40L carries more HBM (Google TPU v5p: 95 GB HBM2e; 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.

Google TPU v5p vs SambaNova SN40L: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v5p 1.53 (459 ÷ 300 W); SambaNova SN40L 1.79 (1,250 ÷ 700 W). SambaNova SN40L wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v5p vs SambaNova SN40L: which is more widely used?

Google TPU v5p: 0 robots and 1 data center publicly running it. SambaNova SN40L: 0 robots and 0 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · Google TPU v5p full page · SambaNova SN40L full page.