
Compatible in all systems that accept an NVIDIA A30
Peak FP64 | 5.2 TFLOPS |
Peak FP64 Tensor Core | 10.3 TFLOPS |
Peak FP32 | 10.3 TFLOPS |
TF32 Tensor Core | 82 TFLOPS | 165 TFLOPS* |
BFLOAT16 Tensor Core | 165 TFLOPS | 330 TFLOPS* |
Peak FP16 Tensor Core | 165 TFLOPS | 330 TFLOPS* |
Peak INT8 Tensor Core | 330 TOPS | 661 TOPS* |
GPU Memory | 24 GB HBM2 |
Memory Bandwidth | 933 GB/s |
Media Engines | 1 Optical Flow Accelerator (OFA) 1 JPEG Decoder (NVJPEG) 4 Video Decoders (NVDEC) |
Thermal Solutions | Passive |
Maximum Power Consumption | 165 W |
System Interface | PCIe Gen 4.0 | 64 GB/s |
NVLink | Third-Generation | 200 GB/s Bidirectional/td> |
Form Factor | 2-Slot, Full Height, Full Length (FHFL) |
Multi-Instance GPU Support | 4 MIGs at 6 GB Each 2 MIGs at 12 GB Each 1 MIG at 24 GB |
vGPU Support | NVIDIA AI Enterprise for VMWare NVIDIA Virtual Compute Server |
*With sparsity