Loading the catalog…
A30 (NVIDIA)
Blurred values are subscriber-only. Sign in to start a free trial — 2 full pages a day — or subscribe for unlimited access.
| Memory Bandwidth Tb S | 0.93 |
|---|---|
| Interconnect | Third-gen NVIDIA NVLINK 200GB/s** |
| Fp32 Tflops | 10.3 |
| Int8 Tops Dense | 330 |
| Gpu Memory Gb | 24 |
| Accelerator Form Factor | PCIe |
| Architecture | Ampere |
| Fp16 Bf16 Tflops Dense | 165 |
| Tdp W | 165 |
| Memory Type | HBM2 |
| Fp16 Bf16 Tflops Sparse | 330 |
| Fp64 Tflops | |
| Int4 Tops Dense | |
| Int4 Tops Sparse | |
| Int8 Tops Sparse | |
| Media Engines | |
| Product Name | |
| Tf32 Tflops Dense |
| Tf32 Tflops Sparse |
|---|
| SKU | A30 |
|---|
| Peak FP64 Tensor Core | |
|---|---|
| BFLOAT16 Tensor Core | |
| Peak INT4 Tensor Core | |
| Multi-Instance GPU (MIG) | |
| Virtual GPU (vGPU) software support | |
| Footnote | |
| TF32 deep learning performance | |
| HPC performance | |
| NVLink Bridge (two A30 PCIe GPUs) deep learning performance | |
| GPU memory (HBM2) | |
| MIG max GPU instances | |
| Structural sparsity performance gain | |
| Hypervisor / virtualization support | |
| GPU-accelerated applications | |
| Certification | |
| Supported deep learning frameworks | |
| GPU-accelerated HPC applications listed | |
| Product URL | |
| Copyright / date |
