Professional

NVIDIA Maxwell architecture with 128 NVIDIA CUDA cores Quad-core ARM Cortex-A57 MPCore processor 4 GB 64-bit LPDDR4 16 GB eMMC 5.1 Flash 12 lanes (3x4 or 4x2) MIPI CSI-2 DPHY 1.1 (1.5 Gbps) HDMI 2.0 or DP1.2 | eDP 1.4 | DSI (1 x2) 2 simultaneous Gigabit Ethernet 1x SDIO / 2x SPI / 6x I2C / 2x I2S / GPIOs

NVIDIA 512-Core Volta GPU with Tensor Cores 8-Core ARM v8.2 64-Bit CPU, 8 MB L2 + 4 MB L3 16 GB 256-Bit LPDDR4x Memory 32 GB eMMC 5.1 Flash Storage (2x) NVDLA DL Accelerator Engines 7-Way VLIW Vision Processor (2x) 4Kp60 | HEVC Video Encoder (2x) 4Kp60 | 12-bit Video Decoder

• Per Sync II Up to 16 Displays, Up to 4 GPUs
• Per system with 2 Sync II, Up to 32 Displays Up to 8 GPUs
• Per Cluster (1 or 2 Sync II per Node), Up to 50 Nodes Up to 200 GPUs
• House Sync, TTL/Composite Input or TTL Output
• Support for up to four sync chains in a single system when 2 Quadro Sync || are used in a single system.
• Form Factor, 4.2 H x 6 L Single Slot

Four NVIDIA Maxwell GPUs Up to 32 users per board 2560 NVIDIA CUDA cores (640 per GPU) 32 GB of GDDR5 memory (8 per GPU) 28 H.264 1080p30 streams ECC protection for increased reliability Server optimization to deliver the best throughput in the data center

• CUDA Parallel-Processing Cores 640
• GPU Memory 4 GB GDDR5
• FP32 Performance 1.894 TFLOPS
• Max Power Consumption 47 W
• Graphics Bus PCI Express 3.0 x 16
• Display Connectors mDP (4)

• CUDA Parallel Processing cores 1280
• GPU Memory 5 GB GDDR5
• FP32 Performance 3.8 TFLOPS
• Max Power Consumption 75 W
• Graphics Bus PCI Express 3.0 x 16
• Display Connectors DP 1.4 (4)

140X HIGHER THROUGHPUT TO KEEP UP WITH EXPLODING DATA SIMPLIFIED OPERATIONS WITH A SINGLE TRAINING AND INFERENCE PLATFORM REAL-TIME INFERENCE FASTER DEPLOYMENT WITH NVIDIA DEEP LEARNING SDK

• CUDA Parallel-Processing Cores 256
• GPU Memory 2 GB GDDR5
• FP32 Performance .641 TFLOPS
• Max Power Consumption 30 W
• Graphics Bus PCI Express 3.0 x 16
• Display Connectors mDP (3)