NVIDIA L4 vs NVIDIA L40 — GPU Comparison (Apr 2026)
NVIDIA L4 (24GB GDDR6, 121 TFLOPS FP16, Ada Lovelace) vs NVIDIA L40 (48GB GDDR6, 181 TFLOPS FP16, Ada Lovelace). Cloud pricing: NVIDIA L4 from $0.39/hr. Compare specs, VRAM, performance, and pricing across 1 cloud providers to find the best GPU for your AI workload.
|
NVIDIA L4
24GB GDDR6 · Ada Lovelace
|
NVIDIA L40
48GB GDDR6 · Ada Lovelace
|
||
|---|---|---|---|
| Specifications | |||
| Manufacturer | NVIDIA | NVIDIA | |
| Architecture | Ada Lovelace | Ada Lovelace | |
| VRAM | 24 GB GDDR6 | 48 GB GDDR6 | |
| Memory Bandwidth | 300 GB/s | 864 GB/s | |
| FP16 (Tensor) | 121.0 TFLOPS | 181.0 TFLOPS | |
| FP32 | 30.3 TFLOPS | 90.5 TFLOPS | |
| TDP | 72W | 300W | |
| Release Year | 2023 | 2023 | |
| Segment | Data center | Data center | |
| Best For | Inference video transcoding lightweight AI workloads | Inference video processing rendering | |
| Cloud Pricing | |||
| Cheapest On-Demand | $0.39/hr | — | |
| Cheapest Spot | — | — | |
| Providers | 1 | 0 | |
| Provider Pricing (On-Demand) | |||
|
$0.39/hr | N/A | |
NVIDIA L4
NVIDIA L40