DEPLOYDatabase

Chip comparison

Google TPU v5p 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 v5pTenstorrent Blackhole
Process nodeTSMC N6
TDP300 W300 W
Memory95 GB HBM2e32 GB GDDR6
Memory bandwidth2,765 GB/s512 GB/s
FP16 (dense)745 TFLOPS
BF16 (dense)459 TFLOPS
INT8 (dense)918 TOPS2,980 TOPS
Form factorOAM (per-chip in v5p pod)PCIe
Announced2023-12-062024-07-01
Released2024-01-012025-01-01

Robots running Google TPU v5p

No robots publicly running it yet.

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Data centers with Google TPU v5p

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Common questions

Google TPU v5p vs Tenstorrent Blackhole: which is faster for training?

Tenstorrent Blackhole has 1.62x the dense FP16/BF16 throughput of the other (Google TPU v5p: 459 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 v5p vs Tenstorrent Blackhole: which has more memory?

Google TPU v5p carries more HBM (Google TPU v5p: 95 GB HBM2e; 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 v5p vs Tenstorrent Blackhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Google TPU v5p 1.53 (459 ÷ 300 W); Tenstorrent Blackhole 2.48 (745 ÷ 300 W). Tenstorrent Blackhole wins at the die level; system-level efficiency also depends on cooling and interconnect.

Google TPU v5p vs Tenstorrent Blackhole: which is more widely used?

Google TPU v5p: 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 v5p full page · Tenstorrent Blackhole full page.