NVIDIA - GPU computing processor
L40 | 48 GB GDDR6 | PCIe 4.0 x16 | 4 x DisplayPort | fanless
Main Specification
| Product Description | NVIDIA - GPU computing processor - L40 - 48 GB |
|---|---|
| Device Type | GPU computing processor |
| Bus Type | PCI Express 4.0 x16 |
| Graphics Engine | NVIDIA L40 |
| Memory | 48 GB GDDR6 |
| CUDA Cores | 18176 |
| Memory Interface | 384-bit |
| Interfaces Details | DisplayPort |
| Fanless | Yes |
| Dimensions (WxDxH) | 26.7 cm x 11.2 cm |
General
| Device Type | GPU computing processor - fanless |
|---|---|
| Bus Type | PCI Express 4.0 x16 |
| Graphics Engine | NVIDIA L40 |
| CUDA Cores | 18176 |
| Interfaces Details | DisplayPort |
| Features | Error Correcting Codes (ECC) Memory, Real-Time Ray Tracing, NEBS Ready, NVIDIA Omniverse, AV1 decode support, NVIDIA Ada Lovelace GPU technology, 4th gen Tensor Cores, secure boot with root of trust, AV1 encode support |
Memory
| Size | 48 GB |
|---|---|
| Technology | GDDR6 SDRAM |
| Bus Width | 384-bit |
| Bandwidth | 864 GBps |
System Requirements
| Additional Requirements | 16 pin PCI Express power connector |
|---|
Miscellaneous
| Power Consumption Operational | 300 watt |
|---|---|
| Compliant Standards | DisplayPort 1.4a |
| Depth | 26.7 cm |
| Height | 11.2 cm |
Product features
Third-generation RT cores
Enhanced throughput and concurrent ray-tracing and shading capabilities improve ray-tracing performance, accelerating renders for product design and architecture, engineering, and construction workflows. See lifelike designs in action with hardware-accelerated motion blur to deliver stunning real-time animations.Fourth-generation tensor cores
Hardware support for structural sparsity and optimized TF32 format provides out-of-the-box performance gains for faster AI and data science model training. Accelerate AI-enhanced graphics capabilities, including DLSS, delivering upscaled resolution with better performance in select applications.Large GPU memory
Tackle memory-intensive applications and workloads like data science, simulation, 3D modeling, and rendering with 48 GB of ultra-fast GDDR6 memory. Allocate memory to multiple users with vGPU software to distribute large workloads among creative, data science, and design teams.Data-center ready
Designed for 24 x 7 enterprise data center operations with power-efficient hardware and components, the NVIDIA L40 is optimized to deploy at scale and deliver maximum performance for a diverse range of data center workloads. The L40 includes secure boot with root of trust technology providing an additional layer of security, and is NEBS Level 3 compliant to meet the data center standards.Key selling points
- Third-generation RT cores
- Fourth-generation tensor cores
- Large GPU memory
- Data-center ready
References
MPN: TCSL40PCIE-PB
What our Customers think about us!
Page generated at:
04/06/2026 20:30:43