NVIDIA A2 vs NVIDIA L40 — GPU Comparison (Jul 2026)
NVIDIA A2 (16GB GDDR6, 18 TFLOPS FP16, Ampere) vs NVIDIA L40 (48GB GDDR6, 181 TFLOPS FP16, Ada Lovelace). Cloud pricing: NVIDIA A2 from $0.22/hr. Compare specs, VRAM, performance, and pricing across 1 cloud providers to find the best GPU for your AI workload.
Bottom Line: NVIDIA A2 vs NVIDIA L40
NVIDIA L40 comes out ahead overall, leading in 5 of 6 compared categories.
Where NVIDIA A2 leads
- TDP (60W vs 300W)
Where NVIDIA L40 leads
- FP16 (181 TFLOPS vs 18 TFLOPS)
- VRAM (48 GB vs 16 GB)
- Memory Bandwidth (864 GB/s vs 200 GB/s)
- FP32 (90.5 TFLOPS vs 4.5 TFLOPS)
- Release Year (2023 vs 2021)
Choose NVIDIA A2 for Edge inference, entry-level AI. Choose NVIDIA L40 for Inference, video processing, rendering.
Frequently Asked Questions
Is NVIDIA A2 or NVIDIA L40 better?
NVIDIA L40 leads in 5 of 6 compared categories. The right choice still depends on the factors that matter most to you.
Which has a better FP16, NVIDIA A2 or NVIDIA L40?
NVIDIA L40 (181 TFLOPS vs 18 TFLOPS).
Which has a better VRAM, NVIDIA A2 or NVIDIA L40?
NVIDIA L40 (48 GB vs 16 GB).
|
NVIDIA A2
16GB GDDR6 · Ampere
|
NVIDIA L40
48GB GDDR6 · Ada Lovelace
|
||
|---|---|---|---|
| Specifications | |||
| Manufacturer | NVIDIA | NVIDIA | |
| Architecture | Ampere | Ada Lovelace | |
| VRAM | 16 GB GDDR6 | 48 GB GDDR6 | |
| Memory Bandwidth | 200 GB/s | 864 GB/s | |
| FP16 (Tensor) | 18.0 TFLOPS | 181.0 TFLOPS | |
| FP32 | 4.5 TFLOPS | 90.5 TFLOPS | |
| TDP | 60W | 300W | |
| Release Year | 2021 | 2023 | |
| Segment | Data center | Data center | |
| Best For | Edge inference entry-level AI | Inference video processing rendering | |
| Cloud Pricing | |||
| Cheapest On-Demand | $0.22/hr | — | |
| Cheapest Spot | — | — | |
| Providers | 1 | 0 | |
| Provider Pricing (On-Demand) | |||
|
$0.22/hr | N/A | |
NVIDIA A2
NVIDIA L40