NVIDIA GeForce RTX 4070 SUPER 12GB vs NVIDIA L40 48GB
The L40 delivers 2.6x the FP8 throughput of the GeForce RTX 4070 SUPER (362 vs 142 TFLOPS dense). The L40 also carries 36 GB more memory (48 GB vs 12 GB).
NVIDIA GeForce RTX 4070 SUPER 12GB
Full specs →NVIDIA L40 48GB
Full specs →Specifications
Performance (TFLOPS)
FLOPS by Precision
What actually differs
The GeForce RTX 4070 SUPER 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 GeForce RTX 4070 SUPER against the L40: FP32 35 vs 91 TFLOPS, FP16 71 vs 181 TFLOPS, FP8 142 vs 362 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 12 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 220 W for the GeForce RTX 4070 SUPER and 300 W for the L40. At FP32 that works out to 0.16 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 4070 SUPER faster than the L40?
At FP8 precision the L40 reaches 362 TFLOPS dense against 142 TFLOPS for the GeForce RTX 4070 SUPER. The performance table on this page lists every published precision for both GPUs.
Which has more memory, the GeForce RTX 4070 SUPER or the L40?
The L40 carries 48 GB of VRAM versus 12 GB for the GeForce RTX 4070 SUPER.
How much power do the GeForce RTX 4070 SUPER and the L40 draw?
The GeForce RTX 4070 SUPER is rated at 220 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 4070 SUPER or the L40 in the cloud?
Yes. Live cloud listings tracked by Flopper start at $0.07 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.
Where to Rent
NVIDIA GeForce RTX 4070 SUPER 12GB
| Provider | Configuration | Price/GPU-hr | Checked | |
|---|---|---|---|---|
 Vast.ai | 4× GeForce RTX 4070 SUPER 12GB Community | $0.07 | 2h ago | View → |
NVIDIA L40 48GB
| Provider | Configuration | Price/GPU-hr | Checked | |
|---|---|---|---|---|
 RunPod | 1× L40 48GB Community | $0.69 | 2h ago | View → |
 CoreWeave | 8× L40 48GB Spot | $0.78 | 2h ago | View → |
 Hyperstack | 1× L40 48GB Spot | $0.80 | 2h ago | View → |
| RunPod | 1× L40 48GB | $0.82 | 2h ago | View → |
 Massed Compute | 1× L40 48GB | $0.88 | 2h ago | View → |
| Hyperstack | 1× L40 48GB | $1.00 | 2h ago | View → |
| CoreWeave | 8× L40 48GB | $1.25 | 2h ago | View → |
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.