DEPLOYDatabase

Chip comparison

SambaNova SN40L vs Tenstorrent Blackhole

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.

FieldSambaNova SN40LTenstorrent Blackhole
Process nodeTSMC N5TSMC N6
TDP700 W300 W
Memory1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5)32 GB GDDR6
Memory bandwidth512 GB/s
FP16 (dense)638 TFLOPS745 TFLOPS
FP8 (dense)1,250 TFLOPS
INT8 (dense)2,980 TOPS
Form factorPCIe (SN40L DataScale system)PCIe
Announced2023-09-192024-07-01
Released2024-01-012025-01-01

Robots running SambaNova SN40L

No robots publicly running it yet.

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Data centers with SambaNova SN40L

No data centers publicly running it yet.

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Common questions

SambaNova SN40L vs Tenstorrent Blackhole: which is faster for training?

SambaNova SN40L has 1.68x the dense FP16/BF16 throughput of the other (SambaNova SN40L: 1,250 TFLOPS; Tenstorrent Blackhole: 745 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

SambaNova SN40L vs Tenstorrent Blackhole: which has more memory?

SambaNova SN40L carries more HBM (SambaNova SN40L: 1500 GB DDR5 (three-tier: 64 MB SRAM + 64 GB HBM3 + 1.5 TB DDR5); Tenstorrent Blackhole: 32 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

SambaNova SN40L vs Tenstorrent Blackhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: SambaNova SN40L 1.79 (1,250 ÷ 700 W); Tenstorrent Blackhole 2.48 (745 ÷ 300 W). Tenstorrent Blackhole wins at the die level; system-level efficiency also depends on cooling and interconnect.

See also: every chip comparison · SambaNova SN40L full page · Tenstorrent Blackhole full page.