DEPLOYDatabase

Chip comparison

NVIDIA A10 Tensor Core GPU vs NVIDIA GB200 Grace Blackwell Superchip

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 A10 Tensor Core GPUNVIDIA GB200 Grace Blackwell Superchip
Process nodeSamsung 8NTSMC 4NP
Transistors (B)28.3
Die size628 mm²
TDP150 W2700 W
Memory24 GB GDDR6384 GB HBM3e
Memory bandwidth600 GB/s16,000 GB/s
FP16 (dense)125 TFLOPS
BF16 (dense)125 TFLOPS
FP8 (dense)9,000 TFLOPS
INT8 (dense)250 TOPS
Form factorPCIeSuperchip (2xB200 + 1xGrace)
Announced2021-04-122024-03-18
Released2021-04-122024-12-01

Robots running NVIDIA A10 Tensor Core GPU

No robots publicly running it yet.

Robots running NVIDIA GB200 Grace Blackwell Superchip

No robots publicly running it yet.

Data centers with NVIDIA A10 Tensor Core GPU

No data centers publicly running it yet.

Common questions

NVIDIA A10 Tensor Core GPU vs NVIDIA GB200 Grace Blackwell Superchip: which is faster for training?

NVIDIA GB200 Grace Blackwell Superchip has 72.00x the dense FP16/BF16 throughput of the other (NVIDIA A10 Tensor Core GPU: 125 TFLOPS; NVIDIA GB200 Grace Blackwell Superchip: 9,000 TFLOPS). Real-world training speed also depends on memory bandwidth, interconnect, and software stack: see the spec diff for those inputs.

NVIDIA A10 Tensor Core GPU vs NVIDIA GB200 Grace Blackwell Superchip: which has more memory?

NVIDIA GB200 Grace Blackwell Superchip carries more HBM (NVIDIA A10 Tensor Core GPU: 24 GB GDDR6; NVIDIA GB200 Grace Blackwell Superchip: 384 GB HBM3e). Memory capacity sets the largest model that fits on one chip without partitioning; memory bandwidth sets inference throughput.

NVIDIA A10 Tensor Core GPU vs NVIDIA GB200 Grace Blackwell Superchip: which is more power-efficient?

Dense FP16/BF16 TFLOPS per watt: NVIDIA A10 Tensor Core GPU 0.83 (125 ÷ 150 W); NVIDIA GB200 Grace Blackwell Superchip 3.33 (9,000 ÷ 2700 W). NVIDIA GB200 Grace Blackwell Superchip wins at the die level; system-level efficiency also depends on cooling and interconnect.

NVIDIA A10 Tensor Core GPU vs NVIDIA GB200 Grace Blackwell Superchip: which is more widely used?

NVIDIA A10 Tensor Core GPU: 0 robots and 0 data centers publicly running it. NVIDIA GB200 Grace Blackwell Superchip: 0 robots and 11 data centers. Empty here means no operator has said publicly, not zero adoption in the market.

See also: every chip comparison · NVIDIA A10 Tensor Core GPU full page · NVIDIA GB200 Grace Blackwell Superchip full page.