The NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture delivers universal, energy-efficient acceleration for video, AI, visual computing, graphics, virtualization, and more. Packaged in a low-profile form factor, L4 is a cost-effective, energy-efficient solution for high throughput and low latency in every server, from the edge to the data center to the cloud.
Form Factor | L4 |
---|---|
FP32 | 30.3 teraFLOPs |
TF32 Tensor Core | 120 teraFLOPS* |
FP16 Tensor Core | 242 teraFLOPS* |
BFLOAT16 Tensor Core | 242 teraFLOPS* |
FP8 Tensor Core | 485 teraFLOPs* |
INT8 Tensor Core | 485 TOPs* |
GPU memory | 24GB |
GPU memory bandwidth | 300GB/s |
NVENC | NVDEC | JPEG decoders | 2 | 4 | 4 |
Max thermal design power (TDP) | 72W |
Form factor | 1-slot low-profile, PCIe |
Interconnect | PCIe Gen4 x16 64GB/s |
Server options | Partner and NVIDIA-Certified Systems with 1–8 GPUs |
DL360 Gen 11 Notes:
− Can support the GPU adapter with Max. length up to 9.5" (full length adapters are not supported) at PCIe Slot 1, 2 and 3. Nvidia GPU L4 will be available in all 3 slots.
− 1 Requires high performance fans
− 2 Can be installed at Slot 1, Slot2 and Slot 3 (if 2 nd processor is selected).
− 3 Max 2x350W CPU, 32x128GB DIMM, and max 10SFF, will need to operated at 20C. Will not be a feasible configuration to support.
− 4 In 8SFF CTO Model, if the Graphics Option is selected with the Processor that is more than 270W, then Maximum of 8 NVMe/ SAS/SATA drives can be selected.
− 5In EDSFF CTO Model, if the Graphics Option is selected with Processor Wattage is more than 270W, then DLC Module must be selected.
HPE DL380 Gen 11 Notes:
− Max = 8
− System memory should be 2x of GPU memory.
− Requires selection of High Performance Fan Kit
− On 12LFF CTO Server, 24SFF CTO Server, or 8SFF CTO Server with Qty3 8SFF drive cages are selected without DLC component then Max of 5 can be selected per server