DEPLOYDatabase

Chip comparison

Google TPU v6 (Trillium) 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.

FieldGoogle TPU v6 (Trillium)Tenstorrent Blackhole
Process nodeTSMC N6
TDP200 W300 W
Memory32 GB HBM332 GB GDDR6
Memory bandwidth1,600 GB/s512 GB/s
FP16 (dense)745 TFLOPS
BF16 (dense)918 TFLOPS
FP8 (dense)1,836 TFLOPS
INT8 (dense)1,836 TOPS2,980 TOPS
Form factorOAM (Trillium pod, up to 256 chips)PCIe
Announced2024-05-142024-07-01
Released2024-12-012025-01-01

Robots running Google TPU v6 (Trillium)

No robots publicly running it yet.

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Data centers with Google TPU v6 (Trillium)

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Common questions

Google TPU v6 (Trillium) vs Tenstorrent Blackhole: which is faster for training?

Google TPU v6 (Trillium) has 2.46x the dense FP16/BF16 throughput of the other (Google TPU v6 (Trillium): 1,836 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.

Google TPU v6 (Trillium) vs Tenstorrent Blackhole: which has more memory?

Tenstorrent Blackhole carries more HBM (Google TPU v6 (Trillium): 32 GB HBM3; Tenstorrent Blackhole: 32 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Google TPU v6 (Trillium) vs Tenstorrent Blackhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v6 (Trillium) 9.18 (1,836 ÷ 200 W); Tenstorrent Blackhole 2.48 (745 ÷ 300 W). Google TPU v6 (Trillium) wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v6 (Trillium) vs Tenstorrent Blackhole: which is more widely used?

Google TPU v6 (Trillium): 0 robots and 1 data center publicly running it. Tenstorrent Blackhole: 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 v6 (Trillium) full page · Tenstorrent Blackhole full page.