NVIDIA L40S 48GB vs NVIDIA L40 48GB

The L40S delivers 2.0x the FP8 throughput of the L40 (733 vs 362 TFLOPS dense).

L40S: Ada Lovelace, 2023 L40: Ada Lovelace, 2023
FP8 dense lead
2.0x
L40S: 733 vs 362 TFLOPS
VRAM
48 vs 48 GB
Same capacity
Bandwidth
864 GB/s vs 864 GB/s
Even
TDP
350 W vs 300 W
L40 draws 50 W less

Specifications

L40S
L40
Architecture
Ada LovelaceAda Lovelace
Launch Year
20232023
Form Factor
PCIePCIe
VRAM
48 GB48 GB
Memory Bandwidth
864 GB/s864 GB/s
TDP
350 W300 W
Process Node
4nm4nm

Performance (TFLOPS)

L40S
L40
FP64
1.4 TFlops
FP32
91.6 TFlops 90.5 TFlops
FP16
362.1 TFlops
733.0 TFLOPS sparse
181.1 TFlops
362.1 TFLOPS sparse
BF16
362.1 TFlops
733.0 TFLOPS sparse
181.1 TFlops
362.1 TFLOPS sparse
FP8
733.0 TFlops
1466.0 TFLOPS sparse
362.0 TFlops
724.0 TFLOPS sparse
INT8
733.0 TFlops
1466.0 TOPS sparse
362.0 TFlops
724.0 TOPS sparse

FLOPS by Precision

What actually differs

Both GPUs launched in 2023: the L40S on Ada Lovelace and the L40 on Ada Lovelace.

Dense throughput for the L40S against the L40: FP32 92 vs 91 TFLOPS, FP16 362 vs 181 TFLOPS, FP8 733 vs 362 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 48 GB against 48 GB, fed at 864 GB/s versus 864 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 350 W for the L40S and 300 W for the L40. At FP32 that works out to 0.26 against 0.30 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 L40S faster than the L40?

At FP8 precision the L40S reaches 733 TFLOPS dense against 362 TFLOPS for the L40. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the L40S or the L40?

Both GPUs carry 48 GB of VRAM. Memory bandwidth is 864 GB/s for the L40S and 864 GB/s for the L40.

How much power do the L40S and the L40 draw?

The L40S is rated at 350 W TDP and the L40 at 300 W. On FP32 throughput per watt, the L40 is the more efficient part.

Can I rent the L40S or the L40 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.69 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA L40S 48GB

ProviderInstancePrice/GPU-hrChecked
DataCrunch
1L40S.20V (spot) $0.69 3h ago View →
Nebius
$0.74 3h ago View →
RunPod
L40S (Community Cloud) $0.79 3h ago View →
Cudo Compute
epyc-genoa-l40s-graphics $0.87 3h ago View →
Massed Compute
gpu_1x_l40s $0.88 3h ago View →
CoreWeave
nvidia-l40s (spot) $0.98 3h ago View →
RunPod
L40S (Secure Cloud) $0.99 3h ago View →
DataCrunch
1L40S.20V (on-demand) $1.37 3h ago View →
Crusoe
$1.50 3h ago View →
Nebius
$1.55 3h ago View →
DigitalOcean
NVIDIA L40S $1.57 3h ago View →
Vultr
vcg-l40s-16c-180g-48vram $1.67 3h ago View →
OVHcloud
l40s-360 $1.80 3h ago View →
CoreWeave
nvidia-l40s (on-demand) $2.25 3h ago View →
All L40S listings and price history →

NVIDIA L40 48GB

ProviderInstancePrice/GPU-hrChecked
RunPod
L40 (Community Cloud) $0.69 3h ago View →
CoreWeave
nvidia-l40 (spot) $0.78 3h ago View →
Hyperstack
$0.80 3h ago View →
RunPod
L40 (Secure Cloud) $0.82 3h ago View →
Massed Compute
gpu_1x_l40 $0.88 3h ago View →
Hyperstack
$1.00 3h ago View →
CoreWeave
nvidia-l40 (on-demand) $1.25 3h ago View →
All L40 listings and price history →

Get Comparison Updates

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