NVIDIA GeForce RTX 4090 D 24GB vs NVIDIA L40 48GB

The L40 delivers 23% more FP8 throughput than the GeForce RTX 4090 D (362 vs 294 TFLOPS dense). The L40 also carries 24 GB more memory (48 GB vs 24 GB).

GeForce RTX 4090 D: Ada Lovelace, 2023 L40: Ada Lovelace, 2023
FP8 dense lead
+23%
L40: 362 vs 294 TFLOPS
VRAM
24 vs 48 GB
24 GB more for the L40
TDP
425 W vs 300 W
L40 draws 125 W less

Specifications

GeForce RTX 4090 D
L40
Architecture
Ada LovelaceAda Lovelace
Launch Year
20232023
Form Factor
PCIePCIe
VRAM
24 GB48 GB
Memory Bandwidth
864 GB/s
TDP
425 W300 W
Process Node
4nm4nm

Performance (TFLOPS)

GeForce RTX 4090 D
L40
FP64
1.1 TFlops No verified data available
FP32
73.5 TFlops 90.5 TFlops
TF32
73.5 TFlops
sparse not published
90.5 TFlops
181.0 TFLOPS sparse
BF16
147.1 TFlops
sparse not published
181.1 TFlops
362.1 TFLOPS sparse
FP16
147.1 TFlops
sparse not published
181.1 TFlops
362.1 TFLOPS sparse
FP8
294.2 TFlops
sparse not published
362.0 TFlops
724.0 TFLOPS sparse
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
588.4 TFlops
sparse not published
362.0 TFlops
724.0 TOPS sparse

FLOPS by Precision

What actually differs

Both GPUs launched in 2023: the GeForce RTX 4090 D on Ada Lovelace and the L40 on Ada Lovelace.

Dense throughput for the GeForce RTX 4090 D against the L40: FP32 74 vs 91 TFLOPS, FP16 147 vs 181 TFLOPS, FP8 294 vs 362 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 24 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 425 W for the GeForce RTX 4090 D and 300 W for the L40. At FP32 that works out to 0.17 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 GeForce RTX 4090 D faster than the L40?

At FP8 precision the L40 reaches 362 TFLOPS dense against 294 TFLOPS for the GeForce RTX 4090 D. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the GeForce RTX 4090 D or the L40?

The L40 carries 48 GB of VRAM versus 24 GB for the GeForce RTX 4090 D.

How much power do the GeForce RTX 4090 D and the L40 draw?

The GeForce RTX 4090 D is rated at 425 W TDP and the L40 at 300 W. On FP32 throughput per watt, the L40 is the more efficient part.

Can I rent the GeForce RTX 4090 D or the L40 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.40 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA GeForce RTX 4090 D 24GB

ProviderConfigurationPrice/GPU-hrChecked
Vast.ai
1× GeForce RTX 4090 D 24GB Community $0.40 1h ago View →
All GeForce RTX 4090 D listings and price history →

NVIDIA L40 48GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× L40 48GB Community $0.69 1h ago View →
CoreWeave
8× L40 48GB Spot $0.78 1h ago View →
Hyperstack
1× L40 48GB Spot $0.80 1h ago View →
RunPod
1× L40 48GB $0.82 1h ago View →
Massed Compute
1× L40 48GB $0.88 1h ago View →
Hyperstack
1× L40 48GB $1.00 1h ago View →
CoreWeave
8× L40 48GB $1.25 1h ago View →
All L40 listings and price history →

Get Comparison Updates

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