NVIDIA GeForce RTX 3080 12GB vs NVIDIA A40 48GB

The A40 delivers 2.4x the FP16 throughput of the GeForce RTX 3080 (150 vs 61 TFLOPS dense). The A40 also carries 36 GB more memory (48 GB vs 12 GB).

GeForce RTX 3080: Ampere, 2022 A40: Ampere, 2021
FP16 dense lead
2.4x
A40: 150 vs 61 TFLOPS
VRAM
12 vs 48 GB
36 GB more for the A40
TDP
350 W vs 300 W
A40 draws 50 W less

Specifications

GeForce RTX 3080
A40
Architecture
AmpereAmpere
Launch Year
20222021
Form Factor
PCIePCIe
VRAM
12 GB48 GB
Memory Bandwidth
696 GB/s
TDP
350 W300 W
Process Node
8nm

Performance (TFLOPS)

GeForce RTX 3080
A40
FP64
0.5 TFlops No verified data available
FP32
30.6 TFlops 37.4 TFlops
TF32
30.6 TFlops
61.3 TFLOPS sparse
74.8 TFlops
149.6 TFLOPS sparse
BF16
61.3 TFlops
122.6 TFLOPS sparse
149.7 TFlops
299.4 TFLOPS sparse
FP16
61.3 TFlops
122.6 TFLOPS sparse
149.7 TFlops
299.4 TFLOPS sparse
FP8
No verified data available No verified data available
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
245.2 TFlops
490.3 TOPS sparse
299.3 TFlops
598.6 TOPS sparse

FLOPS by Precision

What actually differs

The GeForce RTX 3080 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 GeForce RTX 3080 against the A40: FP32 31 vs 37 TFLOPS, FP16 61 vs 150 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 12 GB against 48 GB. 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 350 W for the GeForce RTX 3080 and 300 W for the A40. At FP32 that works out to 0.09 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 GeForce RTX 3080 faster than the A40?

At FP16 precision the A40 reaches 150 TFLOPS dense against 61 TFLOPS for the GeForce RTX 3080. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the GeForce RTX 3080 or the A40?

The A40 carries 48 GB of VRAM versus 12 GB for the GeForce RTX 3080.

How much power do the GeForce RTX 3080 and the A40 draw?

The GeForce RTX 3080 is rated at 350 W TDP and the A40 at 300 W. On FP32 throughput per watt, the A40 is the more efficient part.

Can I rent the GeForce RTX 3080 or the A40 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 2h ago View →
RunPod
1× A40 48GB $0.49 2h ago View →
All A40 listings and price history →

Get Comparison Updates

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