Ada Architecture, CUDA Cores: 18176, FP32: 90.5 TFLOPs, FP16: 181.05 TFLOPs, BFLOAT16: 181.05 TFLOPs, FP8: TFLOPs 362 TFLOPS, INT8: 362 TOPS
£11901.85 inc vat
£9918.21 ex vat
Or £514.14 for 24 monthswith 10% deposit of £1190.19
From virtual workstations to large-scale modeling and simulation, modern visual computing and scientific applications are growing in complexity and quantity. Enterprises need data center solutions that can deliver extreme performance and scale with versatile capabilities to conquer the diverse computing demands of these increasingly complex workloads.
The NVIDIA L40 delivers unprecedented visual computing performance for the data center, providing next-generation graphics, compute, and AI capabilities to GPU-accelerated applications. Based on the Ada Lovelace GPU architecture, the L40 features third-generation RT Cores that enhance real-time ray tracing capabilities, and fourth-generation Tensor Cores with support for the FP8 data format to deliver over a petaflop of inferencing performance. These new features are combined with the latest generation CUDA Cores and 48GB of graphics memory to accelerate visual computing workload from high-performance virtual workstation instances to large-scale digital twins in NVIDIA Omniverse. With up to twice the performance of the previous generation at the same power, the NVIDIA L40 is uniquely suited to provide the visual computing power required by the modern data center.
Graphics Engine | L40 (Ada Lovelace) |
Bus Standard | PCI Express 4.0 (x16) |
CUDA Cores | 18176 |
Tensor Cores | 568 |
RT Cores Cores | 142 |
FP32 | 90.5 teraFLOPs |
TF32 Tensor Core | 90.5 teraFLOPS / 181 teraFLOPS (with Sparsity) |
FP16 Tensor Core | 181.05 teraFLOPS / 362.1 teraFLOPS (with Sparsity) |
BFLOAT16 Tensor Core | 181.05 teraFLOPS / 362.1 teraFLOPS (with Sparsity) |
FP8 Tensor Core | 362 teraFLOPS / 724 teraFLOPS (with Sparsity) |
INT8 Tensor Core | 362 TOPS / 724 TOPS (with Sparsity) |
INT4 Tensor Core | 724 TOPS / 1448 TOPS (with Sparsity) |
GPU Memory | 48GB GDDR6 ECC |
Memory Interface | 384-bit |
Memory Bandwidth | 864 GB/s |
Display Outputs | 4 x DisplayPort 1.4a |
Maximum Digital Resolution | 4x 5K at 60 Hz 2x 8K at 60 Hz 4x 4K at 120 Hz 30-bit Color |
vGPU Software Support | NVIDIA vApps, vPC, vWS |
vGPU Profiles Supported | 1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB |
Graphics APIs | DirectX 12 Ultimate Shader Model 6.6 OpenGL 4.6 Vulkan 1.3 |
NVENC / NVDEC | 3x ENC 3x DEC Includes AV1 Encode and Decode |
Compute APIs | CUDA 12.0 DirectCompute OpenCL 3.0 |
Frame Lock | Supported with optional NVIDIA Quadro Sync II |
NEBS Ready | Level 3 |
Secure Boot with Root of Trust | Supported |
Maximum TDP (Thermal Design Power) | 300 W |
Power Connectors | 16-Pin |
Form Factor | 2 Slot Full Height |
Why not Tell A Friend about this product, all you need to do is fill out their information below and click send.
Get your order delivered the next working day for £5.99, available when ordering Monday - Thursday and before 17:00 on that day if the product is in stock and your payment has cleared.
Get your order delivered the next working day before 12:00pm for £10.98, available when ordering Monday - Thursday and before 17:00 on that day if the product is in stock and your payment has cleared. Some orders if via PayPal and the first customer order may not clear in time.
If you need your order at the weekend, for £12.58, you can specify the day you wish to have it delivered to you, Saturday or Sunday providing your order has been placed by 17:00 on the Friday before.
Economy delivery is available on all orders of any value being shipped within the UK.