Loading the catalog…
NVIDIA A10 (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 | 0.6 |
|---|---|
| Interconnect | PCIe Gen4: 64 GB/s |
| Fp32 Tflops | 31.2 |
| Gpu Memory Gb | 24 |
| Accelerator Form Factor | PCIe |
| Architecture | Ampere |
| Fp16 Bf16 Tflops Dense | 125 |
| Tdp W | 150 |
| Memory Type | GDDR6 |
| Fp16 Bf16 Tflops Sparse | 250 |
| Int8 Tops Dense | 250 |
| Int4 Tops Dense | |
| Int4 Tops Sparse | |
| Int8 Tops Sparse | |
| Product Name | |
| Tf32 Tflops Dense | |
| Tf32 Tflops Sparse |
| SKU | NVIDIA A10 |
|---|
| Tagline | |
|---|---|
| BFLOAT16 Tensor Core | |
| INT8 Tensor Core | |
| RT Cores | |
| Encode / Decode | |
| Max TDP Power | |
| vGPU Software Support | |
| Secure and Measured Boot with Hardware Root of Trust | |
| NEBS Ready | |
| Power Connector | |
| Sparsity footnote | |
| Form factor description | |
| Certification | |
| Virtual workstation performance vs T4 | |
| Inference performance vs T4 | |
| ResNet-50 v1.5 Inference speedup vs T4 | |
| BERT-Large Inference speedup vs T4 | |
| Memory type detail | |
| Tensor Cores generation | |
| RT Cores generation | |
| PCI Express generation | |
| CUDA Cores | |
| Design / OEM compatibility | |
| Security technology | |
| Deep learning framework support | |
| Professional application support | |
| Copyright / date code |
