3U VPX Products Grid
Clear filters
  • 3U VPX Product Selection

    WOLF designs and manufactures 3U VPX video graphics modules that support the VPX REDI and OpenVPX standards. WOLF's 3U VPX boards include advanced NVIDIA GPUs and Xilinx FPGAs, providing video capture, video output, image and data processing, and video encoding to HEVC and AVC.

    High speed GPUs and FPGAs provide the processing power required for High Performance Compute (HPC) and Artificial Intelligence (AI) tasks.

  • VPX3U-A4500E-VO (WOLF-1448)

    NVIDIA Ampere 17.7 TFLOPS, 160 Tensor Cores, 4 DP Out

    • NVIDIA RTX™ GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores, 4 DP outputs
    • 16 GB GDDR6 256-bit memory with up to 512 GB/s
    • PCIe x16 Gen4 with a configurable PCIe switch
    • Module power: TBD-180W, configurable

  • VPX3U-A4500E-CX7 (WOLF-144L)

    HPEC with NVIDIA Ampere and ConnectX-7

    • NVIDIA RTX GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores
    • NVIDIA ConnectX-7 provides the module with up to 100GbE Ethernet and PCIe Gen5 switch
    • 16 GB GDDR6 256-bit memory with up to 512 GB/s
    • Module power: 80-170W, configurable

  • VPX3U-A4500E-IO (WOLF-1440)

    NVIDIA Ampere 17.7 TFLOPS, Video I/O, SDI, DP, Analog

    • NVIDIA RTX™ GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores
    • 16 GB GDDR6 256-bit memory with up to 512 GB/s
    • WOLF FGX for video format conversion
    • Module power: TBD-190W, configurable

  • VPX3U-A4500E-FGX2-IO (WOLF-144D)

    NVIDIA Ampere 17.7 TFLOPS, Video I/O, 12G-SDI, DP

    • NVIDIA RTX™ GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores, 4 DP outputs
    • 16 GB GDDR6 256-bit memory with up to 512 GB/s
    • WOLF FGX2 for video format conversion
    • Module power: TBD-190W, configurable

  • VPX3U-A4500E-FGX2-CV (WOLF-144A)

    NVIDIA Ampere 17.7 TFLOPS, 12G-SDI, Analog, DP Output

    • NVIDIA RTX™ GA104 GPU with 17.66 TFLOPS FP32 peak performance*, 5888 CUDA Cores, 184 Tensor Cores, 46 RT Cores, 4 outputs
    • 12G-SDI and Analog output support
    • 16 GB GDDR6 256-bit memory with up to 512 GB/s
    • PCIe x16 Gen4 with a configurable PCIe switch
    • Module power: TBD-190W, configurable

  • VPX3U-A2000E-FGX2-4IO (WOLF-1470)

    NVIDIA Ampere 8.25 TFLOPS, Video I/O, SDI, DP, Analog

    • NVIDIA RTXTM GA107, 2560 CUDA cores, 80 Tensor cores, 20 RT cores, peak performance 8.25 TFLOPS*
    • 8 GB GDDR6 memory, 128 Bit, 192 GB/s max
    • Four 12G-SDI or ARINC 818 or DP/DVI/HDMI output, two SDI or ARINC 818 input, CVBS/RGB input
    • Module power: TBD-120W, configurable

  • VPX3U-A2000E-WMXM-VO (WOLF-1475)

    NVIDIA Ampere 8.25 TFLOPS, four video outputs

    • NVIDIA RTXTM GA107, 2560 CUDA cores, 80 Tensor cores, 20 RT cores, peak performance 8.25 TFLOPS*
    • 8 GB GDDR6 memory, 128 Bit, 192 GB/s max
    • Up to 4 outputs, options for DisplayPort/DVI/HDMI
    • Module power: 40-80W, configurable

  • VPX3U-A2000-VO (WOLF-14H5)

    NVIDIA Ampere 8.25 TFLOPS, four video outputs

    • NVIDIA RTXTM GA107, 2560 CUDA cores, 80 Tensor cores, 20 RT cores, peak performance 8.25 TFLOPS*
    • 8 GB GDDR6 memory, 128 Bit, 192 GB/s max
    • Up to 4 outputs, options for DisplayPort/DVI/HDMI
    • Module power: 40-80W, configurable

  • VPX3U-ORIN-CX7-SBC (WOLF-14T0)

    NVIDIA Orin, ConnectX-7, Video I/O, SBC Profile

    • Embedded Ampere GPU with 2048 CUDA cores (5.3 TFLOPS) & 64 Gen3 Tensor cores (275 TOPS Int8)*
    • Embedded 12-core NVIDIA Cortex ARM64 CPU, 2.2GHz
    • 64 GB LPDDR5 256-bit memory with up to 205 GB/s
    • ConnectX-7, up to 100GbE Ethernet, PCIe Gen5
    • SDI input/output, DP MST output, Analog output
    • Module power: configurable from 80W - 120W

  • VPX3U-ORIN-CX7-HPC (WOLF-14TZ)

    NVIDIA Orin, ConnectX-7, HPC, Payload Profile

    • Embedded Ampere GPU with 2048 CUDA cores (5.3 TFLOPS) & 64 Gen3 Tensor cores (275 TOPS Int8)*
    • Embedded 12-core NVIDIA Cortex ARM64 CPU, 2.2GHz
    • 64 GB LPDDR5 256-bit memory with up to 205 GB/s
    • ConnectX-7, up to 100GbE Ethernet, PCIe Gen5
    • Module power: configurable from 60W - 100W

  • VPX3U-XAVIER-CX6-SBC (WOLF-12T0)

    Xavier Industrial, ConnectX-6, Video I/O, SBC Profile

    • Embedded Volta GPU with 512 CUDA cores (1.4 TFLOPS) & 64 Tensor cores (20 TOPS Int8)
    • Embedded 8-core NVIDIA Carmel ARM64 CPU, 2.26GHz
    • 32 GB LPDDR4 256-bit memory with up to 137 GB/s
    • ConnectX-6, up to 100GbE Ethernet, PCIe Gen4
    • SDI inputs/outputs, DP outputs, Analog outputs
    • Module power: configurable from 50W - 90W

  • VPX3U-XAVIER-CX6-HPC (WOLF-12TZ)

    Xavier Industrial, ConnectX-6, Payload Profile

    • Embedded Volta GPU with 512 CUDA cores (1.4 TFLOPS) & 64 Tensor cores (20 TOPS Int8)
    • Embedded 8-core NVIDIA Carmel ARM64 CPU, 2.26GHz
    • 32 GB LPDDR4 256-bit memory, 137 GB/s, ECC support
    • ConnectX-6, up to 100GbE Ethernet, PCIe Gen4
    • Module power: configurable from 40W - 70W

  • VPX3U-RTX5000E-COAX-CV (WOLF-1349)

    NVIDIA Turing 9.5 TFLOPS, WOLF FGX, Coaxial Connections

    • NVIDIA Quadro Turing TU104 GPU, 9.5 TFLOPS peak performance*, 3072 CUDA Cores, 384 Tensor Cores
    • SOSA™ Aligned with support for SOSA slot profile
    • WOLF FGX provides support for additional video formats such as SDI and Analog
    • Module power: configurable from 50 to 175W

  • VPX3U-RTX5000E-VO (WOLF-1348)

    NVIDIA Turing, 9.5 TFLOPS, 384 Tensor Cores, 4 Video Outputs

    • NVIDIA RTX Turing TU104 GPU with 9.5 TFLOPS*, 3072 CUDA Cores, 384 Tensor Cores, 48 RT Cores
    • 16 GB GDDR6 256-bit memory with up to 448 GB/s
    • Four video outputs, DP/HDMI/DVI
    • Module power: 50-165W

  • VPX3U-RTX5000E-SWITCH (WOLF-134S)

    NVIDIA Turing HPEC, PCIe Gen4 Switch, 10GigE Switch

    • NVIDIA Quadro Turing TU104 GPU provides 9.5 TFLOPS peak performance* of HPEC processing
    • PCIe Gen4 Switch
    • 10 Gig Ethernet Switch
    • Module power: 60-160W

  • VPX3U-RTX5000E-16PCIE (WOLF-134C)

    NVIDIA Turing RTX5000 HPEC, PCIe Gen4 Switch, SOSA Aligned

    • NVIDIA Quadro Turing TU104 GPU, 9.5 TFLOPS peak performance*, 3072 CUDA Cores, 384 Tensor Cores
    • SOSA™ Aligned with support for SOSA payload slot profile 14.6.13
    • PCIe interface up to Gen4, up to x16 on P1/P2
    • Module power: configurable from 60 to 190W

  • VPX3U-P5200E-VO (WOLF-1116)

    Chip-Down NVIDIA Quadro Pascal GP104, 8.7 TFLOPS, 4 Video Outputs

    • NVIDIA P5200E, 8.7 TFLOPS, GPGPU/Inference
    • Chip-down WOLF design and fabrication meets military and aerospace specifications
    • 4 independent DisplayPort 1.4 outputs
    • 16 GB GDDR5 memory with NVIDIA GPUDirect™ DMA
    • Operating power configurable hard cap: 40 – 150W

  • VPX3U-P2000E-VO (WOLF-1178)

    Chip-Down NVIDIA Quadro Pascal GP107, 2.3 TFLOPS, 4 Video Outputs

    • NVIDIA® Quadro® PascalTM GP107, 2.3 TFLOPS, GPGPU Engine
    • Chip-down WOLF design and fabrication meets military and aerospace specifications
    • 4 independent DisplayPort 1.4 outputs
    • 4 GB GDDR5 memory with NVIDIA GPUDirect™ DMA 
    • Operating power configurable hard cap: 30 – 50W

  • VPX3U-P2000E-SDI-4IO (WOLF-1110)

    Chip-Down NVIDIA Quadro Pascal GP107, 4 SDI I/O, Analog I/O

    • NVIDIA GP107, 2.3 TFLOPS, GPGPU Engine
    • Chip-down WOLF design and fabrication meets military and aerospace specifications
    • Up to four 3G-SDI inputs and four outputs
    • Up to four analog inputs and/or outputs
    • 4 GB GDDR5 memory with NVIDIA GPUDirect™ DMA
    • Operating power configurable hard cap: 40 – 60W

  • VPX3U-RTX3000E-VO (WOLF-1368)

    NVIDIA Quadro Turing, 5.3 TFLOPS, 240 Tensor Cores, DP Outputs

    • NVIDIA Quadro Turing TU106 GPU, 5.3 TFLOPS peak performance*
    • 1920 CUDA Cores, 240 Tensor Cores, 30 RT Cores
    • 6 GB GDDR6 192-bit memory with up to 336 GB/s
    • Chip-down WOLF design and fabrication with full component traceability
    • Four DisplayPort outputs
    • Module power: configurable from 30 to 80W

  • VPX3U-TESLA-P6-HPC (WOLF-1116)

    ProdEOL

    NVIDIA Tesla Pascal P6, 6.2 TFLOPS with HPC Mode & GRID vGPU

    • NVIDIA® Tesla® PascalTM P6 16nm FinFET GPU
    • 6.2 TFLOPS, 2048 CUDA® core GPGPU Engine
    • High Performance Compute (HPC) mode
    • NVIDIA GRID™ vGPU virtualization with up to 16 vGPU instances
    • Operating power configurable hard cap: 40 – 90W

  • VPX3U-P5000-VO (WOLF-1116)

    NVIDIA Quadro Pascal P5000 Video Processing and Graphics Output Module

    • NVIDIA P5000, 6.2 TFLOPS, GPGPU Engine
    • 4 independent DisplayPort 1.4 outputs
    • 16 GB GDDR5 memory with NVIDIA GPUDirect™ DMA
    • Operating power configurable hard cap: 40 – 100W

  • VPX3U-P3000-VO (WOLF-1116)

    NVIDIA Quadro Pascal P3000 Video Processing and Graphics Output Module

    • NVIDIA P3000, 3.9 TFLOPS, GPGPU Engine
    • 4 independent DisplayPort 1.4 outputs
    • 6 GB GDDR5 memory
    • Operating power configurable hard cap: 40 – 75W

  • VPX3U-P5000-SDI-4IO (WOLF-1110)

    NVIDIA Quadro Pascal P5000, 4 SDI I/O, Analog I/O

    • NVIDIA® Quadro® Pascal™ P5000, 6.2 TFLOPS GPGPU Engine
    • Up to four 3G-SDI inputs and four 3G-SDI outputs
    • Up to four analog inputs and/or outputs
    • 16 GB GDDR5 memory with NVIDIA GPUDirect™ DMA technology
    • Operating power configurable hard cap: 50 – 120W

  • VPX3U-P3000-SDI-4IO (WOLF-1110)

    NVIDIA Quadro Pascal P3000, 4 SDI I/O, Analog I/O

    • NVIDIA® Quadro® Pascal™ P3000, 3.9 TFLOPS GPGPU Engine
    • Up to four 3G-SDI inputs and four 3G-SDI outputs
    • Up to four analog inputs and/or outputs
    • 6 GB GDDR5 memory 
    • Operating power configurable hard cap: 50 – 85W

This website uses cookies. Please see our Privacy Policy for more information.