DEPLOYDatabase

Chip comparison

Tenstorrent Blackhole vs Tenstorrent Wormhole

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.

FieldTenstorrent BlackholeTenstorrent Wormhole
Process nodeTSMC N6GlobalFoundries 12nm
TDP300 W160 W
Memory32 GB GDDR612 GB GDDR6
Memory bandwidth512 GB/s288 GB/s
FP16 (dense)745 TFLOPS148 TFLOPS
INT8 (dense)2,980 TOPS590 TOPS
Form factorPCIePCIe (n300, n150)
Announced2024-07-012024-07-01
Released2025-01-012024-08-01

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Robots running Tenstorrent Wormhole

No robots publicly running it yet.

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Data centers with Tenstorrent Wormhole

No data centers publicly running it yet.

Common questions

Tenstorrent Blackhole vs Tenstorrent Wormhole: which is faster for training?

Tenstorrent Blackhole has 5.03x the dense FP16/BF16 throughput of the other (Tenstorrent Blackhole: 745 TFLOPS; Tenstorrent Wormhole: 148 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

Tenstorrent Blackhole vs Tenstorrent Wormhole: which has more memory?

Tenstorrent Blackhole carries more HBM (Tenstorrent Blackhole: 32 GB GDDR6; Tenstorrent Wormhole: 12 GB GDDR6). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

Tenstorrent Blackhole vs Tenstorrent Wormhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Tenstorrent Blackhole 2.48 (745 ÷ 300 W); Tenstorrent Wormhole 0.93 (148 ÷ 160 W). Tenstorrent Blackhole wins at the die level; system-level efficiency also depends on cooling and interconnect.

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