NVIDIA L2 24GB vs NVIDIA L40 48GB

The L40 delivers 88% more FP16 throughput than the L2 (181 vs 97 TFLOPS dense). The L40 also carries 24 GB more memory (48 GB vs 24 GB).

L2: Ada Lovelace, 2024 L40: Ada Lovelace, 2023
FP16 dense lead
+88%
L40: 181 vs 97 TFLOPS
Memory
24 vs 48 GB
24 GB more for the L40
Bandwidth
300 GB/s vs 864 GB/s
L40 moves data faster
See rental pricing from $0.49/hr Download comparison sheet

Share this page

NVIDIA L2 24GB vs NVIDIA L40 48GB

A post with this link shows the card on the Image tab as its preview.

Printable version →

Specifications

L2
L40
Architecture
Ada LovelaceAda Lovelace
Launch Year
20242023
Form Factor
PCIePCIe
Memory
24 GB48 GB
Memory Bandwidth
300 GB/s864 GB/s
TDP
—300 W
Process Node
TSMC 4N4nm

Performance (TFLOPS)

L2
L40
FP64
No verified data available No verified data available
FP32
24 TFLOPS 91 TFLOPS
TF32
48 TFLOPS
sparse not published
91 TFLOPS
181 TFLOPS sparse
BF16
97 TFLOPS
sparse not published
181 TFLOPS
362 TFLOPS sparse
FP16
97 TFLOPS
sparse not published
181 TFLOPS
362 TFLOPS sparse
FP8
No verified data available362 TFLOPS
724 TFLOPS sparse
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
193 TOPS
sparse not published
362 TOPS
724 TOPS sparse

FLOPS by Precision

What actually differs

The L2 is the newer part: Ada Lovelace, launched in 2024, against the L40's Ada Lovelace from 2023. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the L2 against the L40: FP32 24 vs 91 TFLOPS, FP16 97 vs 181 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 24 GB against 48 GB, fed at 300 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.

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 L2 faster than the L40?

At FP16 precision the L40 reaches 181 TFLOPS dense against 97 TFLOPS for the L2. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the L2 or the L40?

The L40 carries 48 GB of memory versus 24 GB for the L2. Memory bandwidth is 300 GB/s for the L2 and 864 GB/s for the L40.

Can I rent the L2 or the L40 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.49 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA L40 48GB

ProviderConfigurationPrice/GPU-hrChecked
2× L40 48GB Community $0.49 3h ago View →
1× L40 48GB Community $0.69 3h ago View →
GPU.ai
1× L40 48GB Community $0.69 3h ago View →
Oblivus
1× L40 48GB Reserved $0.74 3h ago View →
GPU.ai
1× L40 48GB $0.78 3h ago View →
8× L40 48GB Spot $0.78 3h ago View →
Thunder Compute
1× L40 48GB $0.79 9d ago View →
Thunder Compute
2× L40 48GB $0.79 9d ago View →
1× L40 48GB Spot $0.80 3h ago View →
1× L40 48GB $0.82 3h ago View →
Shadeform Massed Compute capacity
1× L40 48GB $0.88 3h ago View →
Thunder Compute
4× L40 48GB $0.99 9d ago View →
Thunder Compute
8× L40 48GB $0.99 9d ago View →
1× L40 48GB $1.00 3h ago View →
Oblivus
1× L40 48GB $1.05 3h ago View →
8× L40 48GB $1.25 3h ago View →
Shadeform Excess Supply capacity
8× L40 48GB $1.38 3h ago View →
All L40 listings and price history →

Get Comparison Updates

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

© 2026 Flopper.io - Compare the GPUs Powering AI