NVIDIA L40S 48GB GDDR6 PCIe Gen 4.0 x16 Dual Slot Ada Lovelace GPU | TCSL40SPCIE-PB
Brand: NVIDIA | Category: GPUs
SKU: TCSL40SPCIE-PB | Part #: TCSL40SPCIE-PB
Contact for Pricing — Request a Quote
About the NVIDIA L40S 48GB GDDR6 PCIe Gen 4.0 x16 Dual Slot Ada Lovelace GPU | TCSL40SPCIE-PB
The NVIDIA L40S 48GB GDDR6 PCIe Gen 4.0 x16 Dual Slot Ada Lovelace GPU | TCSL40SPCIE-PB from NVIDIA is enterprise-grade GPUs hardware built for data centers. The NVIDIA L40S 48GB is a professional PCIe Gen 4.0 data centre GPU built on the Ada Lovelace architecture, delivering exceptional AI inference, training, and graphics workloads for enterprise and cloud environments. Featuring 48GB of ECC-protected GDDR6 memory and third-generation RT Cores, it is ideal for AI/ML, HPC, and virtualised workloads in GCC data centres. Available in brand new condition. NVIDIA gpus products are trusted by enterprises and data centers worldwide. Available from Omnixon Global. Contact our sales team to request a quote.
Technical Specifications
| Brand | NVIDIA |
| Category | GPUs |
| SKU | TCSL40SPCIE-PB |
| Part Number | TCSL40SPCIE-PB |
| Condition | New |
| Model | L40S |
| GPU Architecture | Ada Lovelace |
| Process Node | TSMC 4N (optimised for NVIDIA) |
| Transistor Count | 76.3 Billion |
| CUDA Cores | 18,176 |
| Tensor Cores (4th Gen) | 568 |
| RT Cores (3rd Gen) | 142 |
| FP32 (Single Precision) Compute | 91.6 TFLOPS |
| TF32 Tensor Core Performance | 183 TFLOPS | 366 TFLOPS (sparse) |
| FP16 / BF16 Tensor Core Performance | 362.05 TFLOPS | 724.1 TFLOPS (sparse) |
| FP8 Tensor Core Performance | 733 TFLOPS | 1,457 TFLOPS (sparse) |
| INT8 Tensor Core Performance | 733 TOPS | 1,457 TOPS (sparse) |
| RT Core Performance | 191.9 TRTOPS |
| Memory Capacity | 48 GB |
| Memory Type | GDDR6 |
| Memory Bus Width | 384-bit |
| Memory Bandwidth | 864 GB/s |
| ECC Support | Yes — SECDED ECC |
| Host Interface | PCI Express Gen 4.0 x16 |
| PCIe Bandwidth (Bidirectional) | 64 GB/s |
| Display Outputs | 4x DisplayPort 1.4 |
| Max Display Resolution | 7680 x 4320 (8K) @ 60Hz |
| NVLink Support | Not Supported |
| GPUDirect RDMA | Supported |
| Form Factor | Full Height, Full Length (FHFL), Dual Slot |
| Card Length | 267 mm |
| Card Width (Slot) | Dual Slot |
| Power Connector | 1x 16-pin PCIe Gen 5 (adapter included for 2x 8-pin) |
| Cooling | Active — Blower-Style Single Fan |
| Thermal Design Power (TDP) | 300W |
| Minimum System Power Supply | 650W recommended |
| Operating Temperature | 0°C to 80°C GPU Junction (Tjmax) |
| Storage Temperature | -20°C to 85°C |
| Supported Operating Systems | Windows Server 2019/2022, RHEL 8/9, Ubuntu 20.04/22.04 LTS, VMware vSphere 7.x/8.x |
| Virtualisation Support | NVIDIA vGPU, MIG (Multi-Instance GPU) |
| CUDA Compute Capability | 8.9 |
| Supported Precision Formats | FP64, FP32, TF32, FP16, BF16, INT8, FP8 |