Premio KCO-3000-RPL Intel 14th Gen Core Edge AI Workstations with Dual GPU Support
The Premio KCO-3000-RPL series is a family of edge AI workstations for 12th to 14th Gen Intel Core processors on the Q670E chipset, with dual GPU support, a PCIe Gen5 x16 slot, DDR4 up to 128 GB, an internal 500 W Flex power supply, USB 3.2 Gen 2x2 and four DP++ outputs. The KCO-3000-RPL series suits edge AI inference, manufacturing, light industrial and digital signage deployments.
- Dual GPU Support: Room for two NVIDIA RTX PRO Blackwell or RTX Ada cards from the AVL, fed by the internal 500 W power supply.
- PCIe Gen5 x16 Expansion: One PCIe x16 Gen5 slot, one x16 slot with four Gen4 lanes and two open-ended PCIe x4 slots for add-in cards.
- 12th to 14th Gen Intel Core: LGA1700 on the Intel Q670E chipset with four DDR4 DIMM sockets for up to 128 GB of memory.
- Internal 500W Flex Power Supply: A built-in 100 to 240 V AC power supply through an IEC C14 inlet, so there is no external adapter.
- USB 3.2 Gen 2×2 and Quad DP++: A 20 Gbps USB-C port, six USB 3.2 Gen 2 ports and four DP++ outputs for independent displays.
Intel
Linux
Windows
Quad Display Support
2.5GbE
Type C
USB3
3x M.2
4x PCIe
1x SIM
Wi-Fi
RAID
NVMe SSD
CE
FCC
KCO-3000-RPL Description
Teams that develop AI models on desk workstations often run into trouble when the same model has to run on site, where the hardware also needs serial ports, digital I/O and a single mains inlet. Premio built the KCO-3000-RPL series as an edge AI workstation for that step, with room for two NVIDIA RTX cards, a PCIe Gen5 x16 slot and an internal 500 W power supply in a chassis with a tool-less washable dust filter. The range was designed by C&T Solution, which became Premio Taiwan in January 2026.
The KCO-3000-RPL design centres on an LGA1700 socket on the Intel Q670E chipset for 12th, 13th and 14th Gen Core i3 to i9 processors at 35 W or 65 W, with four DDR4 2133 to 2666 DIMM sockets for up to 128 GB. Expansion pairs one PCIe x16 Gen5 slot with an x16 slot carrying four Gen4 lanes and two open-ended PCIe x4 slots at Gen4 and Gen3, and the GPU AVL lists the NVIDIA RTX PRO 4000 Blackwell, RTX PRO 4000 Blackwell SFF, RTX PRO 2000 Blackwell, RTX 4000 Ada, RTX 4000 SFF Ada and RTX 2000 Ada. Two M.2 M key NVMe sockets, four SATA III ports with RAID 0, 1, 5 and 10, and space for one 3.5″ or two 2.5″ drives cover storage.
The series currently has one model. The KCO-3000-RPL-500W is the 500 W build, with dual GPU support, one 2.5GbE and one GbE port, a 20 Gbps USB 3.2 Gen 2×2 Type-C port, six USB 3.2 Gen 2, two front USB 3.2 Gen 1 and four USB 2.0 ports, four DP++ outputs and six COM ports. Among Premio edge AI workstations, the KCO-2000-RPL keeps the I/O in a more compact unit with a 250 W supply and low-profile GPUs, and the KCO-6000-ARL moves to Intel Core Ultra Series 2 with an NPU and PCIe Gen5 risers.
In practice the KCO-3000-RPL series suits edge AI inference, model work close to the production line, manufacturing and digital signage. It runs from 100 to 240 V AC through an IEC C14 inlet, operates from 0 °C to 50 °C, and uses CPU and system fans behind the dust filter. TPM 2.0, UEFI Secure Boot and Intel AMT are supported with Windows 11 and Linux, and the range is UL listed to UL 62368-1 with CE, FCC and UKCA marks. Rack-mount brackets are available for cabinet installs.
KCO-3000-RPL Specifications
| Overview | |
|---|---|
| Brand & Model | Premio KCO-3000-RPL |
| Features | Embedded Expandable GPU Industrial USB C |
| Performance | |
| Processor Series | Intel Core 14th Gen Raptor Lake Refresh Intel Core 12th Gen Alder Lake Intel Core 13th Gen Raptor Lake |
| GPU / AI Accelerator | Discrete GPU (PCIe) |
| Supported GPUs | RTX 4000 SFF Ada NVIDIA RTX PRO 2000 Blackwell: 4352 CUDA Cores, 16GB GDDR7 ECC, 70W NVIDIA RTX PRO 4000 Blackwell: 8960 CUDA Cores, 24GB GDDR7 ECC, 140W NVIDIA RTX PRO 4000 Blackwell SFF Edition: 8960 CUDA Cores, 24GB GDDR7 ECC, 70W NVIDIA RTX 2000 Ada Generation: 2816 CUDA Cores, 88 Tensor Cores, 16GB GDDR6 ECC, 70W NVIDIA RTX 4000 Ada Generation: 6144 CUDA Cores, 192 Tensor Cores, 20GB GDDR6 ECC, 130W |
| AI Performance | 192–1,290 TOPS |
| Number of GPUs | Dual GPU Support |
| GPU Family | NVIDIA RTX Ada NVIDIA RTX PRO Blackwell |
| GPU Architecture | NVIDIA Ada Lovelace NVIDIA Blackwell |
| Memory | 4x DDR4 2666MHz LONG-DIMM Slots, 128GB |
| Chipset | Intel Q670E |
| PCIe Gen Support | PCIe 5.0 |
| BIOS | AMI UEFI |
| Secure Crypto Processor | TPM 2.0 (Trusted Platform Module) |
| Operating System | Linux Windows 11 |
| Graphics | |
| Integrated GPU | Intel UHD Series |
| Display Standards | DP++ |
| Multi Display Support | Quad Display Support |
| Display Outputs | 4x Display Ports |
| Audio | |
| Codec | RealTek ALC888S, HD Audio |
| Interface | Line-In Line-Out Mic-In |
| I/O | |
| Ethernet | 2x Ethernet Ports |
| 1x 2.5 GbE LAN [RJ45] 1x GbE LAN [RJ45] | |
| LAN Controllers | Intel I219LM Intel I225V |
| USB | 13x USB Ports |
| 1x USB 3.2 Gen 2x2 [Type C] 2x USB 3.2 Gen 1 [Type A] 4x USB 2.0 [Type A] 6x USB 3.2 Gen 2 [Type A] | |
| Serial | 6x Serial Ports |
| 1x RS232/422/485 [Board] 2x RS232 [DB9] 3x RS232 [Board] | |
| Digital I/O | DIO [4-in, 4-out] |
| Remote Management | Intel AMT |
| Expansion | |
| M.2 | 3x M.2 Expansion Slots |
| 1x M.2 E-Key [PCIe x1 Gen3/USB 2.0] [2230] 1x M.2 M-Key [PCIe x4 Gen4/SATA] [2242/2260/2280] 1x M.2 M-Key [PCIe x4 Gen4] [2242/2260/2280] | |
| PCIe | 4x PCIe Slots |
| 1x PCIe [x16 Slot] [Gen5] 1x PCIe [x16 Slot] [x4 Signal] [Gen4] 1x PCIe [x4 Slot] [Gen3] 1x PCIe [x4 Slot] [Gen4] | |
| SIM Slots | 1x SIM Slots |
| Wireless Connectivity | Optional WiFi/Bluetooth |
| Storage | |
| Storage | 2x 2.5" HDD/SSD 2x M.2 SSD 4x SATA Ports |
| NVMe | NVMe SSD Support |
| RAID | RAID 0 (Striping) RAID 1 (Mirroring) RAID 5 (Striping & Distributed Parity) RAID 10 (Mirroring & Striping) |
| Power | |
| Power Input | 100-240V AC AC Power Supply Included |
| Power Support Modes | AT: PWR on Input ATX: Press Button to Power |
| Environmental Conditions | |
| Thermal Dissipation | Onboard Fan |
| Operating Temperature | 0°C to 50°C [32°F to 122°F] |
| Storage Temperature | -40°C to 85°C [-40°F to 185°F] |
| Humidity | 10-90% (Non-condensing) |
| Certification | IEC 62368-1 CB CE FCC IC (ICES-003) UKCA UL 62368-1 |
| Mechanical Properties | |
| Weight | 5.6 Kg (12.3 Lbs) |
| Dimensions | 334mm x 300mm x 133mm (13.15" x 11.81" x 5.24") |
| Mounting Options | Desktop Rack Mount |
No specifications match your search.
See product variants.
KCO-3000-RPL Variants
Premio KCO-3000-RPL-500W Intel 14th Gen Core i9 Edge AI Workstation with Dual GPU Support, PCIe Gen5 and USB 3.2 Gen 2×2
KCO-3000-RPL-500W with dual GPU support, PCIe Gen5 x16, 500W PSU and USB 3.2 Gen 2x2
| Overview | |
|---|---|
| Brand & Model | Premio KCO-3000-RPL-500W |
No related media available for this product series.
Official Premio USA Distributor
Things Embedded is an official Premio USA distributor, and we supply the KCO-3000-RPL series configured and tested, with the processor, DDR4 memory, NVMe and SATA storage, the NVIDIA GPU cards and a Windows 11 or Linux image fitted before it ships. Within the Premio range, the KCO-6000-ARL moves to Intel Core Ultra Series 2 with an NPU, PCIe Gen5 risers and a 24 to 48V DC input, and the VCO-6000-RPL takes one large GPU on a 600W power board in a wide-temperature machine vision PC. If you are unsure whether one or two GPUs suit your workload, our team can help you size it.
Across our range, the KCO-3000-RPL series sits with our industrial GPU computers, our edge AI computers and our NVIDIA RTX PRO Blackwell computers.
Consult. Design. Integrate.
Things Embedded is a leading USA supplier of industrial computing and edge AI systems. We combine technical expertise with a collaborative approach to deliver optimal solutions for your application. Whether it’s an off-the-shelf platform or a custom design, we stay at the forefront of the latest technologies to ensure your success at the edge. Our team works closely with you from concept through deployment, providing guidance, engineering support, and integration expertise every step of the way.
Connect with our solutions experts today to review your requirements and find the ideal solution fit for your application.