-
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.
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
COMING SOON
| Specification | Details |
|---|---|
| GPU Architecture | NVIDIA Ada Lovelace |
| GPU Memory | 48 GB GDDR6 with ECC |
| Memory Bandwidth | 864 GB/s |
| Tensor Cores | INT8 |
| BF16 | |
| 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 |
Download
Only logged in customers who have purchased this product may leave a review.
Reviews
There are no reviews yet.