Nvidia L20 Enterprise 48GB

GPU Architecture: NVIDIA Ada Lovelace

GPU Memory: 48 GB GDDR6 with ECC

Memory Bandwidth: 864 GB/s

Tensor Cores:

  • INT8 | FPB Tensor Core®: 239 | 239 TFLOPS
  • BF16 | FP16 Tensor Core*: 119.5 | 119.5 TFLOPS
  • TF32 Tensor Core*: 59.8 TFLOPS

FP32 Processing Power: 59.8 TFLOPS

FP64 Processing Power: N/A

RT Core: Yes

MIG Support: Yes

L2 Cache: 96 MB

Media Engine:

  • 3 NVENC (+AV1)
  • 3 NVDEC
  • 4 NVJPEG

Power Consumption: 275 W

Form Factor: 2-slot FHFL

Interconnect: PCIe Gen4 x16 with a speed of 64 GB/s



  • img

    NVIDIA L20: Elevating Processing Power with Ada Lovelace Architecture

    Embodying the cutting-edge Ada Lovelace architecture, the NVIDIA L20 stands as a technological marvel in the realm of GPUs. With 48 GB of GDDR6 memory featuring ECC and a formidable memory bandwidth of 864 GB/s, it ensures efficient data handling for demanding applications. The tensor cores, including INT8, FPB, BF16, and FP16, contribute to the L20's robust processing capabilities, reaching up to 59.8 TFLOPS for FP32 operations. With support for RT cores, Multi-Instance GPU (MIG), and a substantial 96 MB L2 Cache, the L20 is designed for versatility and optimal workload management. Its power-efficient design, consuming 275 W and housed in a 2-slot FHFL form factor, positions the L20 as a dynamic solution for various computing needs.

Specification Details
GPU Architecture NVIDIA Ada Lovelace
GPU Memory 48 GB GDDR6 with ECC
Memory Bandwidth 864 GB/s
Tensor Cores INT8
TF32 Tensor Core*: 59.8 TFLOPS
FP32 Processing Power 59.8 TFLOPS
FP64 Processing Power N/A
RT Core Yes
MIG Support Yes
L2 Cache 96 MB
Media Engine 3 NVENC (+AV1), 3 NVDEC, 4 NVJPEG
Power Consumption 275 W
Form Factor 2-slot FHFL
Interconnect PCIe Gen4 x16 with a speed of 64 GB/s



    There are no reviews yet.

    Be the first to review “Nvidia L20 Enterprise 48GB”
    Review now to get coupon!

    Your email address will not be published. Required fields are marked *

    You may also like…