DEPLOYDatabase

Chip comparison

Huawei Ascend 910C 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.

FieldHuawei Ascend 910CTenstorrent Blackhole
Process nodeSMIC N+2 (~7nm)TSMC N6
TDP500 W300 W
Memory128 GB HBM2e32 GB GDDR6
Memory bandwidth3,200 GB/s512 GB/s
FP16 (dense)800 TFLOPS745 TFLOPS
BF16 (dense)800 TFLOPS
INT8 (dense)1,600 TOPS2,980 TOPS
Form factorOAMPCIe
Announced2024-09-192024-07-01
Released2025-01-012025-01-01

Robots running Huawei Ascend 910C

No robots publicly running it yet.

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Data centers with Huawei Ascend 910C

No data centers publicly running it yet.

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Common questions

Huawei Ascend 910C vs Tenstorrent Blackhole: which is faster for training?

Huawei Ascend 910C has 1.07x the dense FP16/BF16 throughput of the other (Huawei Ascend 910C: 800 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.

Huawei Ascend 910C vs Tenstorrent Blackhole: which has more memory?

Huawei Ascend 910C carries more HBM (Huawei Ascend 910C: 128 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.

Huawei Ascend 910C vs Tenstorrent Blackhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: Huawei Ascend 910C 1.60 (800 ÷ 500 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 · Huawei Ascend 910C full page · Tenstorrent Blackhole full page.