| Product | Integrated Video (Included with Motherboard) | NVIDIA® T400 4GB GDDR6 - PCIe 3.0 x16 - Active Cooling (3x mDP) | NVIDIA® T1000 8GB GDDR6 - PCIe 3.0 x16 - Active Cooling (4x mDP) | NVIDIA® RTX A1000 - 8GB GDDR6 - PCIe 4.0 x8 - Active Cooling (4x mDP) | NVIDIA® RTX A2000 - 12GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4x mDP) | NVIDIA® RTX A4500 - 20GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4xDP) |
| Price Change | ||||||
| Action | Select | Select | Select | Select | Select | Select |
| Manufacturer | PNY | PNY | PNY | PNY | PNY | |
| Part Number | VCNT4004GB-PB | VCNT10008GB-PB | VCNRTXA1000LP-PB | VCNRTXA200012GB-PB | VCNRTXA4500-PB | |
| Main Specifications | ||||||
| Host Interface | PCI Express 3.0 x16 | PCI Express 3.0 x16 | PCI Express 4.0 x8 | PCI Express 4.0 x16 | PCI Express 4.0 x16 | |
| Product Type | Workstation | Workstation | Workstation | Workstation | Workstation | |
| Product Line | NVIDIA Professional Graphics | NVIDIA Professional Graphics | NVIDIA Professional Graphics | |||
| Memory Technology | GDDR6 | GDDR6 | GDDR6 | GDDR6 with ECC | GDDR6 with ECC | |
| Memory Capacity | 4 GB | 8 GB | 8 GB | 12 GB GDDR6 with ECC | 20 GB GDDR6 with ECC | |
| Max Displays | 4 Displays | 4 Displays | 4 Displays | 4 Displays | 4 Displays | |
| Detailed Specifications | ||||||
| Processor | NVIDIA Turing | NVIDIA Turing | Ampere | Ampere | Ampere | |
| Memory Bandwidth | 80 GB/s | 160 GB/s | 192 GB/sec | 288 GB/sec | 640 GB/sec | |
| Memory Interface | 64-bit | 128-bit | 128-bit | 192-bit | 320-bit | |
| Memory Clock Speed | 6001 MHz | |||||
| Peak Single-Precision Performance | 23.7 TFLOPS | |||||
| API Support | CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran Shader Model 5.1 (OpenGL 4.5 and DirectX 12) | CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran Shader Model 5.1 (OpenGL 4.5 and DirectX 12) | ||||
| Transistor Count | 8.7 Billion | 13.25 Billion | 28.3 Billion | |||
| Graphics Resolution | Max Digital Resolution: 7680 x 4320 at 60 Hz | Max Digital Resolution: 7680 x 4320 at 60 Hz | 2x 7680 x 4320 at 60 Hz | |||
| Streaming Processor Cores | 384 CUDA Parallel-Processing Cores | 896 CUDA Parallel-Processing Cores | 2307 CUDA Cores | 3328 CUDA Cores | 7168 CUDA Cores | |
| NVIDIA Tensor Cores | 72 | 104 | 224 | |||
| Tensor Performance | 13.2 TFLOPS | 63.9 TFLOPS | 182.2 TFLOPS | |||
| Peak Single Precision FP32 Performance | 1.094 TFLOPS | 2.50 TFLOPS | 6.74 TFLOPS | 8.0 TFLOPS | ||
| Multi-GPU Scalability | 2-way low profile (2-slot and 3-slot bridges) connects 2x NVIDIA RTX A4500 | |||||
| NVLink Interconnect | Not Supported | 112.5 GB/sec bidirectional | ||||
| NVIDIA RT Cores | 18 | 26 | 56 | |||
| RT Core Performance | 15.6 TLOPS | 46.2 TFLOPS | ||||
| DisplayPort Output | 4x DisplayPort 1.4a | |||||
| Mini DisplayPort Output | x3 | x4 | 4x mDisplayPort 1.4a | 4x mDP Latching | ||
| Max Graphics Card Power (W) | 30W | 50W | 50W | 70W | 200W | |
| Minimum Recommended Power, Single Card (W) | 300W | |||||
| Minimum Recommended Power, 2-Way (W) | 500 | |||||
| Minimum Recommended Power, 3-Way (W) | 750 | |||||
| Minimum Recommended Power, 4-Way (W) | 1000 | |||||
| Supplementary Power Connectors | 1x 8-pin PCIe | |||||
| Thermal Solution | Ultra-quiet active fansink | Ultra-quiet active fansink | Active Fan | Active Heatsink | Active Heatsink | |
| Slot Height | Low-Profile Single Slot | Low-Profile Single Slot | Single Slot | 2-Slot | 2-Slot | |
| Lithography | 8N | NVIDIA Custom Process | 8nm | 8nm | |||
| Dimensions | 2.713” H x 6.137” L | 2.7" H x 6.4" L | 2.713" H x 6.6" L | 4.4" H x 10.5" L | ||
| Action | Select | Select | Select | Select | Select | Select |