Product | 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 A2000 - 12GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4x mDP) | NVIDIA® RTX A4000 - 16GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4xDP) | NVIDIA® RTX A6000 - 48GB GDDR6 - PCIe 4.0 x16 - Active Cooling (4xDP) |
Action | Select | Select | Select | Select | Select |
Main Specifications | |||||
Host Interface | PCI Express 3.0 x16 | PCI Express 3.0 x16 | PCI Express 4.0 x16 | 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 with ECC | GDDR6 with ECC | GDDR6 |
Memory Capacity | 4 GB | 8 GB | 12 GB GDDR6 with ECC | 16 GB GDDR6 with ECC | 48 GB |
Max Displays | 4 Displays | 4 Displays | 4 Displays | 4 Displays | |
Detailed Specifications | |||||
Processor | NVIDIA Turing | NVIDIA Turing | Ampere | Ampere (GA104) | Ampere (GA102) |
Memory Bandwidth | 80 GB/s | 160 GB/s | 288 GB/sec | 448 GB/sec | 768 GB/s |
Memory Interface | 64-bit | 128-bit | 192-bit | 256-bit | 384-bit |
Core Clock Speed | 1455 MHz Base Clock 1860 MHz Boost Clock | ||||
Memory Clock Speed | 6001 MHz | 2000 MHz 16 Gbps effective | |||
L2 Cache Size | 6 MB | ||||
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) | CUDA 8.5, OpenCL 2.0 Shader Model 6.5, OpenGL 4.6, DirectX 12 Ultimate (12_2), Vulkan 1.2 | ||
Texture Fill Rate | 625 GTexel/s | ||||
Transistor Count | 13.25 Billion | 17.4 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 | Max Digital Resolution: 7680 x 4320 x36 bpp at 60 Hz | 7680 x 4320 x36 bpp at 60 Hz |
Streaming Processor Cores | 384 CUDA Parallel-Processing Cores | 896 CUDA Parallel-Processing Cores | 3328 CUDA Cores | 6144 CUDA Cores | 10752 Shading Units |
NVIDIA Tensor Cores | 104 | 192 | 336 | ||
Tensor Performance | 63.9 TFLOPS | ||||
Peak Double Precision FP64 Performance | 1,250 GFLOPS (1:32) | ||||
Peak Single Precision FP32 Performance | 1.094 TFLOPS | 2.50 TFLOPS | 8.0 TFLOPS | 38.7 TFLOPS | |
Peak Half Precision FP16 Performance | 40.00 TFLOPS (1:1) | ||||
Deep Learning TFLOPS | 153.4 TFLOPS | ||||
Multi-GPU Scalability | NVLINK 2-way low profile (2-slot and 3-slot bridges) connects 2x NVIDIA RTX A6000 | ||||
NVLink Interconnect | 112.5 GB/s (bidirectional) | ||||
NVIDIA RT Cores | 26 | 48 | 84 | ||
RT Core Performance | 15.6 TLOPS | ||||
VR Ready | Yes | ||||
Vulkan API | 1.2 | ||||
NVIDIA CUDA™ Technology | Yes | Yes | |||
DisplayPort Output | 4x DisplayPort 1.4a | 4x DisplayPort 1.4a | |||
Mini DisplayPort Output | x3 | x4 | 4x mDP Latching | ||
Max Graphics Card Power (W) | 30W | 50W | 70W | 140W | 300W |
Minimum Recommended Power, Single Card (W) | 300W | 700W | |||
Minimum Recommended Power, 2-Way (W) | 500 | 850 | |||
Minimum Recommended Power, 3-Way (W) | 850 | 1000 | |||
Minimum Recommended Power, 4-Way (W) | 1000 | 1200 | |||
Supplementary Power Connectors | 1x 6-pin PCIe | 1x 8-pin EPS | |||
Thermal Solution | Ultra-quiet active fansink | Ultra-quiet active fansink | Active Heatsink | Active Heatsink | Active Heatsink |
Slot Height | Low-Profile Single Slot | Low-Profile Single Slot | 2-Slot | Single Slot | 2-Slot |
Lithography | 8nm | 8nm | Samsung 8nm | ||
Dimensions | 2.713” H x 6.137” L | 2.713" H x 6.6" L | 4.4” H x 9.5” L | 4.4" (H) x 10.5" (L) | |
Action | Select | Select | Select | Select | Select |