NVIDIA RTX A2000 6GB vs NVIDIA A40 48GB

The A40 delivers 4.7x the FP32 throughput of the RTX A2000 (37 vs 8 TFLOPS dense). The A40 also carries 42 GB more memory (48 GB vs 6 GB).

RTX A2000: Ampere, 2021 A40: Ampere, 2021
FP32 dense lead
4.7x
A40: 37 vs 8 TFLOPS
VRAM
6 vs 48 GB
42 GB more for the A40
Bandwidth
288 GB/s vs 696 GB/s
A40 moves data faster
TDP
70 W vs 300 W
RTX A2000 draws 230 W less

Specifications

RTX A2000
A40
Architecture
AmpereAmpere
Launch Year
20212021
Form Factor
PCIePCIe
VRAM
6 GB48 GB
Memory Bandwidth
288 GB/s696 GB/s
TDP
70 W300 W
Process Node
8nm

Performance (TFLOPS)

RTX A2000
A40
FP64
0.1 TFlops No verified data available
FP32
8.0 TFlops 37.4 TFlops
TF32
No verified data available74.8 TFlops
149.6 TFLOPS sparse
BF16
No verified data available149.7 TFlops
299.4 TFLOPS sparse
FP16
The vendor publishes only the 2:4 sparse figure for this precision
63.9 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
No verified data available299.3 TFlops
598.6 TOPS sparse

FLOPS by Precision

What actually differs

Both GPUs launched in 2021: the RTX A2000 on Ampere and the A40 on Ampere.

Dense throughput for the RTX A2000 against the A40: FP32 8 vs 37 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 6 GB against 48 GB, fed at 288 GB/s versus 696 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 70 W for the RTX A2000 and 300 W for the A40. At FP32 that works out to 0.11 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 RTX A2000 faster than the A40?

At FP32 precision the A40 reaches 37 TFLOPS dense against 8 TFLOPS for the RTX A2000. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the RTX A2000 or the A40?

The A40 carries 48 GB of VRAM versus 6 GB for the RTX A2000. Memory bandwidth is 288 GB/s for the RTX A2000 and 696 GB/s for the A40.

How much power do the RTX A2000 and the A40 draw?

The RTX A2000 is rated at 70 W TDP and the A40 at 300 W. On FP32 throughput per watt, the A40 is the more efficient part.

Can I rent the RTX A2000 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.