NVIDIA A40 48GB vs NVIDIA A10G 24GB

The A40 delivers 2.1x the FP16 throughput of the A10G (150 vs 70 TFLOPS dense). The A40 also carries 24 GB more memory (48 GB vs 24 GB).

A40: Ampere, 2021 A10G: Ampere, 2022
FP16 dense lead
2.1x
A40: 150 vs 70 TFLOPS
VRAM
48 vs 24 GB
24 GB more for the A40
Bandwidth
696 GB/s vs 600 GB/s
A40 moves data faster
TDP
300 W vs 300 W
Same power budget

Specifications

A40
A10G
Architecture
AmpereAmpere
Launch Year
20212022
Form Factor
PCIePCIe
VRAM
48 GB24 GB
Memory Bandwidth
696 GB/s600 GB/s
TDP
300 W300 W
Process Node
8nm

Performance (TFLOPS)

A40
A10G
FP32
37.4 TFlops 35.0 TFlops
FP16
149.7 TFlops
299.4 TFLOPS sparse
70.0 TFlops
sparse not published
BF16
149.7 TFlops
299.4 TFLOPS sparse
70.0 TFlops
sparse not published
INT8
299.3 TFlops
598.6 TOPS sparse
140.0 TFlops
sparse not published

FLOPS by Precision

What actually differs

The A10G is the newer part: Ampere, launched in 2022, against the A40's Ampere from 2021. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the A40 against the A10G: FP32 37 vs 35 TFLOPS, FP16 150 vs 70 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 48 GB against 24 GB, fed at 696 GB/s versus 600 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 300 W for the A40 and 300 W for the A10G. At FP32 that works out to 0.12 against 0.12 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the A40 faster than the A10G?

At FP16 precision the A40 reaches 150 TFLOPS dense against 70 TFLOPS for the A10G. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the A40 or the A10G?

The A40 carries 48 GB of VRAM versus 24 GB for the A10G. Memory bandwidth is 696 GB/s for the A40 and 600 GB/s for the A10G.

How much power do the A40 and the A10G draw?

The A40 is rated at 300 W TDP and the A10G at 300 W. On FP32 throughput per watt, the A40 is the more efficient part.

Can I rent the A40 or the A10G in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.35 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA A40 48GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× A40 48GB Community $0.35 4h ago View →
RunPod
1× A40 48GB $0.44 4h ago View →
All A40 listings and price history →

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.