NVIDIA L40 (48GB GDDR6)
- 48GB GDDR6
- Memory
- 864GB/s
- Memory bandwidth
- Q4 2022
- Released
Price history
PLACEHOLDERWhat it costs to rent a NVIDIA L40
The NVIDIA L40 is an Ada Lovelace-architecture mid-range NVIDIA GPU with 48GB of GDDR6 memory and 864 GB/s of memory bandwidth, released Q4 2022. It is built for inference, fine-tuning and mixed production workloads.
Renting one currently costs between $0.40 and $1.25 per GPU-hour across the 9 cloud providers we track. The cheapest live rate is $0.40/hr from Vast.ai (spot). All rates below are normalised to a single GPU per hour so providers with multi-GPU nodes compare like-for-like.
Where to rent the L40
37 offers · 9 providers| Provider | Tier | Config | Total VRAM | Billing | $ / GPU / hr | Total / hr | Availability |
|---|---|---|---|---|---|---|---|
CoreWeave
|
Enterprise | 8× L40 | 384GB | On-demand | $1.25 | $10.00 | — |
Hyperstack
|
GPU cloud | 1× L40 | 48GB | Spot | $0.80 | $0.80 | — |
|
Hyperstack
|
GPU cloud | 1× L40 | 48GB | On-demand | $1.00 | $1.00 | — |
|
Hyperstack
|
GPU cloud | 1× L40 | 48GB | On-demand | $1.00 | $1.00 | — |
Massed Compute
|
GPU cloud | 1× L40 | 48GB | On-demand | $0.86 | $0.86 | In stock |
|
Massed Compute
|
GPU cloud | 1× L40 | 48GB | On-demand | $0.86 | $0.86 | — |
|
Massed Compute
|
GPU cloud | 2× L40 | 96GB | On-demand | $0.86 | $1.72 | — |
|
Massed Compute
|
GPU cloud | 2× L40 | 96GB | On-demand | $1.72 | $3.44 | In stock |
|
Massed Compute
|
GPU cloud | 4× L40 | 192GB | On-demand | $0.86 | $3.44 | — |
|
Massed Compute
|
GPU cloud | 4× L40 | 192GB | On-demand | $3.44 | $13.76 | In stock |
RunPod
|
GPU cloud | 1× L40 | 48GB | Community | $0.69 | $0.69 | In stock |
|
RunPod
|
GPU cloud | 1× L40 | 48GB | On-demand | $0.82 | $0.82 | In stock |
|
RunPod
|
GPU cloud | 2× L40 | 96GB | Community | $0.69 | $1.38 | In stock |
Sesterce
|
GPU cloud | 1× L40 | 48GB | On-demand | $0.97 | $0.97 | In stock |
|
Sesterce
|
GPU cloud | 2× L40 | 96GB | On-demand | $1.09 | $2.18 | In stock |
|
Sesterce
|
GPU cloud | 4× L40 | 192GB | On-demand | $1.64 | $6.56 | In stock |
Vast.ai
|
GPU cloud | 1× L40 | 48GB | Spot | $0.47 BEST | $0.47 | In stock |
|
Vast.ai
|
GPU cloud | 1× L40 | 48GB | On-demand | $0.53 | $0.53 | In stock |
|
Vast.ai
|
GPU cloud | 2× L40 | 96GB | Spot | $0.47 | $0.93 | In stock |
|
Vast.ai
|
GPU cloud | 2× L40 | 96GB | On-demand | $0.53 | $1.05 | In stock |
|
Vast.ai
|
GPU cloud | 3× L40 | 144GB | Spot | $0.40 | $1.20 | In stock |
|
Vast.ai
|
GPU cloud | 3× L40 | 144GB | On-demand | $0.45 | $1.36 | In stock |
|
Vast.ai
|
GPU cloud | 4× L40 | 192GB | Spot | $0.47 | $1.87 | In stock |
|
Vast.ai
|
GPU cloud | 4× L40 | 192GB | On-demand | $0.57 | $2.30 | In stock |
|
Vast.ai
|
GPU cloud | 8× L40 | 384GB | Spot | $0.47 | $3.73 | In stock |
|
Vast.ai
|
GPU cloud | 8× L40 | 384GB | On-demand | $0.57 | $4.59 | In stock |
GPU.ai
|
Marketplace | 1× L40 | 48GB | On-demand | $0.87 | $0.87 | In stock |
|
GPU.ai
|
Marketplace | 2× L40 | 96GB | On-demand | $1.85 | $3.70 | In stock |
Oblivus
|
Marketplace | 1× L40 | 48GB | Reserved | $0.74 | $0.74 | — |
|
Oblivus
|
Marketplace | 1× L40 | 48GB | On-demand | $1.05 | $1.05 | — |
|
Oblivus
|
Marketplace | 2× L40 | 96GB | Reserved | $0.74 | $1.48 | — |
|
Oblivus
|
Marketplace | 2× L40 | 96GB | On-demand | $1.05 | $2.10 | — |
|
Oblivus
|
Marketplace | 4× L40 | 192GB | Reserved | $0.74 | $2.96 | — |
|
Oblivus
|
Marketplace | 4× L40 | 192GB | On-demand | $1.05 | $4.20 | — |
|
Oblivus
|
Marketplace | 8× L40 | 384GB | Reserved | $0.74 | $5.92 | — |
|
Oblivus
|
Marketplace | 8× L40 | 384GB | On-demand | $1.05 | $8.40 | — |
Thunder Compute
|
Marketplace | 1× L40 | 48GB | On-demand | $0.79 | $0.79 | — |
The five most established providers first, then the rest. Each row is a provider’s cheapest current offer, normalised to a single GPU per hour. Tier reflects company type, not a quality score. We do not collect vCPU or RAM per instance yet, so those columns are omitted rather than estimated.
Technical specifications
| FP64 | 1.4 TFLOPS |
|---|---|
| FP32 | 91 TFLOPS |
| FP16/BF16 | 181 TFLOPS |
- Memory
- 48 GB
- Memory bandwidth
- 864 GB/s
- TDP
- 300 W
- INT8
- 362 TOPS
- Die size
- 608 mm²
- Transistors
- 76.3 B
- Released
- 13 Oct 2022
| Architecture | Ada Lovelace |
|---|---|
| Memory | 48 GB GDDR6 ECC |
| Bandwidth | 864 GB/s |
| Form factor | passive dual-slot PCIe |
| Cooling | server airflow |
| Power | 300 W |
- Class
- Mid-range
- Cloud providers
- 9 tracked
- Price range
- $0.40 – $1.25 / GPU / hr
Other mid-range cards
NVIDIA L40S
SNAPSHOT 2026-07-29 19:42:49 UTC · BACK TO THE FULL INDEX