DEPLOYDatabase

Chip comparison

NVIDIA A100 Tensor Core GPU 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.

FieldNVIDIA A100 Tensor Core GPUTenstorrent Blackhole
Process nodeTSMC N7TSMC N6
Transistors (B)54
Die size826 mm²
TDP400 W300 W
Memory80 GB HBM2e32 GB GDDR6
Memory bandwidth2,039 GB/s512 GB/s
FP16 (dense)312 TFLOPS745 TFLOPS
BF16 (dense)312 TFLOPS
INT8 (dense)624 TOPS2,980 TOPS
Launch price (list)$10,000
Form factorSXM4PCIe
Announced2020-05-142024-07-01
Released2020-05-142025-01-01

Robots running NVIDIA A100 Tensor Core GPU

No robots publicly running it yet.

Robots running Tenstorrent Blackhole

No robots publicly running it yet.

Data centers with NVIDIA A100 Tensor Core GPU

No data centers publicly running it yet.

Data centers with Tenstorrent Blackhole

No data centers publicly running it yet.

Common questions

NVIDIA A100 Tensor Core GPU vs Tenstorrent Blackhole: which is faster for training?

Tenstorrent Blackhole has 2.39x the dense FP16/BF16 throughput of the other (NVIDIA A100 Tensor Core GPU: 312 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.

NVIDIA A100 Tensor Core GPU vs Tenstorrent Blackhole: which has more memory?

NVIDIA A100 Tensor Core GPU carries more HBM (NVIDIA A100 Tensor Core GPU: 80 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.

NVIDIA A100 Tensor Core GPU vs Tenstorrent Blackhole: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: NVIDIA A100 Tensor Core GPU 0.78 (312 ÷ 400 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 · NVIDIA A100 Tensor Core GPU full page · Tenstorrent Blackhole full page.