Many AI edge computers come with dedicated AI accelerators from Intel, Google, Gyrfalcon, and others. But as we’ve seen with Cincoze GM-1000 embedded mini PC, some include support for more traditional GPUs, in this case, an NVIDIA Quadro Embedded P2000 MXM module.
Ryzen Embedded V1807B powered Vecow MIG-1000 AI edge PC is another such solution with up to 64GB DDR4, four DisplayPort outputs, and a PCIe x16 slot for dual-slot graphics cards from Nvidia or AMD for AI processing performance and/or extra video outputs.
- SoC – AMD Ryzen Embedded V1807B quad-core processor with Radeon Vega 11 graphics; 35-54W TDP
- System Memory – 2x DDR4 3200MHz SO-DIMM, up to 64GB
- Storage – 1x SATA-III port, 1x M.2 Key M socket (2280, PCIe x4) for NVMe SSDs
- Video Output – 4x DisplayPort up to 4096 x 2160 @ 60Hz
- Realtek ALC662, 5.1 Channel HD Audio codec
- 1x Mic-in, 1x Line-out, 1x Line-in jacks
- Networking – 2x Gigabit Ethernet ports via Realtek RTL8111G GbE controllers
- USB – 2x USB 3.0 ports, 2x USB 2.0 ports
- Serial – 2x COM RS-232 ports
- Expansion – 1x PCIe x 16 Slot with support for dual-slot graphics cards
- Misc – Power, HDD LEDs, HW monitor (temperature, voltages. Auto throttling control when CPU overheats)
- Power Supply – 9V to 55V DC via 2-pin terminal block up to 750 Watts
- Dimensions – 162.6 x 203.6 x 385.0mm
- Weight – 5.3 kg
- Temperature Range – Operating: 0°C to 60°C; storage: -40°C to 85°
- Humidity – 5% to 95% Humidity, non-condensing
- IEC 61373 – 2010
- Railway applications – Rolling Stock Equipment, Shock and Vibration Test
- EMC – CE, FCC, EN50155, EN50121-3-2
The embedded AI computer supports Windows 10/7 and Linux distributions, and can optionally wall-mounted via a mounting bracket. Vecow says the PC supports NVIDIA Tesla/Quadro/GeForce and AMD Radeon Graphics, as well as the latest NVIDIA RTX 30 series powered by Ampere architecture featuring DLSS AI acceleration up to max 10496 CUDA cores for expanded AI computing capability.
Vecow MIG-1000 is more much powerful and power-hungry than solutions typically showcased on CNX Software. Yet it’s still decided to edge computing applications in autonomous vehicles, traffic vision, medical imaging, gaming, and AIoT/Industry 4.0 applications.