US 
Premio LLM-1U-RPL Intel 12th to 14th Gen Core 1U Edge AI Servers with Redundant Power
The Premio LLM-1U-RPL series is a family of 1U edge AI servers on 12th to 14th Gen Intel Core processors, with one PCIe x16 Gen4 slot or two PCIe x8 Gen4 slots for NVIDIA RTX GPUs, two 600 W supplies in 1+1 redundancy on AC or -48 V DC, three 2.5GbE ports, triple 4K display and hot-swap SSD bays. The LLM-1U-RPL series suits edge AI inference, machine vision and manufacturing deployments.
- Intel 12th to 14th Gen Core: LGA 1700 Core i3 to i9 processors up to 65 W on an Intel Q670E chipset, with up to 64 GB of DDR4.
- PCIe Gen4 GPU Slots: One PCIe x16 Gen4 slot or two x8 Gen4 slots, with RTX PRO Blackwell and RTX Ada cards on the approved list.
- Redundant 600 W Power: Two 600 W supplies in 1+1 redundancy, on 115 to 230 V AC or on -36 to -72 V DC for telecom rooms.
- Hot-Swap Storage and Fans: Two hot-swap 2.5″ SATA SSD bays with RAID 0 and 1, M.2 NVMe, and three hot-swap dual smart fans.
- Three 2.5GbE and Triple 4K: Three Intel 2.5GbE ports, two DisplayPort 1.4a and one HDMI output, eight USB 3.2 ports and four COM ports.
Intel- Linux
- Windows
Triple Display Support
2.5GbE
USB3- 3x M.2
- 2x PCIe
- 1x SIM
- 4G
- 5G
- Wi-Fi
- NVMe SSD
- Ignition Control
- CE
- FCC
- 1x PCIe
LLM-1U-RPL Description
When an AI model moves from a pilot to the production line, it usually ends up in a rack, and that rack often has a single unit of space left and a supply the server has to match. The Premio LLM-1U-RPL series answers that with 1U edge AI servers that take a professional NVIDIA RTX GPU, run from AC mains or a -48 V DC feed, and keep running if one of the two power supplies fails.
Every LLM-1U-RPL server shares the same design. LGA 1700 Intel Core i3 to i9 processors from the 12th, 13th and 14th Gen sit on an Intel Q670E chipset, at 35 W or up to 65 W, with two DDR4 3200 SO-DIMM sockets for up to 64 GB. The riser gives either one PCIe x16 Gen4 slot or two PCIe x8 Gen4 slots, and Premio’s approved GPU list covers the RTX PRO 4500, 4000, 4000 SFF and 2000 Blackwell, the RTX 5000, 4500, 4000, 4000 SFF and 2000 Ada, and the RTX A1000. Two hot-swap 2.5″ SATA SSD bays with RAID 0 and 1 sit beside M.2 M key NVMe and M.2 B key sockets, and three Intel 2.5GbE ports, three 4K display outputs, eight USB 3.2 ports and four COM ports handle the I/O. Three hot-swap dual smart fans and a dust filter keep the airflow serviceable.
The range splits by slot layout and power input. The LLM-1U-RPL-1E16-600W-AC pairs one x16 slot for a dual-slot GPU with two 600 W supplies on 115 to 230 V AC, and the LLM-1U-RPL-1E16-600W-DC is the same build on -36 to -72 V DC for telecom and DC-powered rooms. The LLM-1U-RPL-2E8-600W-AC splits the riser into two x8 slots for a GPU alongside a second PCIe card on AC power, and the LLM-1U-RPL-2E8-600W-DC does the same on DC.
In practice the LLM-1U-RPL series suits edge AI inference, machine vision and manufacturing data work in an equipment room or a line-side rack. Each server is rated 0 °C to 35 °C with 0.6 m/s airflow (to 25 °C with GPUs above 210 W), is designed to comply with MIL-STD-810H for shock and vibration, and carries UL 62368-1, CE and FCC Class A marks. Premio designs and builds its systems in Greater Los Angeles, with research, design and engineering in Taipei, under an IEC 62443-4-1 certified development process.
LLM-1U-RPL Specifications
| Overview | |
|---|---|
| Brand & Model | Premio LLM-1U-RPL |
| Features | Expandable GPU Redundant Power Supply |
| Performance | |
| Processor Series | Intel Core 14th Gen Raptor Lake Refresh Intel Core 12th Gen Alder Lake Intel Core 13th Gen Raptor Lake |
| Processor Models | Intel Core i3-14100T: 2.7~4.4GHz, 4 Cores, 8 Threads, 12MB Cache, 35W Intel Core i5-14500: 2.6~5.0GHz, 14 Cores, 20 Threads, 24MB Cache, 65W Intel Core i5-14500T: 1.7~4.8GHz, 14 Cores, 20 Threads, 24MB Cache, 35W Intel Core i7-14700: 2.1~5.4GHz, 20 Cores, 28 Threads, 33MB Cache, 65W Intel Core i7-14700T: 1.3~5.2GHz, 20 Cores, 28 Threads, 33MB Cache, 35W Intel Core i9-14900: 2.0~5.8GHz, 24 Cores, 32 Threads, 36MB Cache, 65W Intel Core i9-14900T: 1.1~5.5GHz, 24 Cores, 32 Threads, 36MB Cache, 35W Intel Core i3-12100E: 3.2~4.2GHz, 4 Cores, 8 Threads, 12MB Cache, 60W Intel Core i3-12100TE: 2.1~4.0GHz, 4 Cores, 8 Threads, 12MB Cache, 35W Intel Core i3-13100E: 3.3~4.4GHz, 4 Cores, 8 Threads, 12MB Cache, 60W Intel Core i3-13100TE: 2.4~4.1GHz, 4 Cores, 8 Threads, 12MB Cache, 35W Intel Core i5-12500E: 2.9~4.5GHz, 6 Cores, 12 Threads, 18MB Cache, 65W Intel Core i5-12500TE: 1.9~4.3GHz, 6 Cores, 12 Threads, 18MB Cache, 35W Intel Core i5-13500E: 2.4~4.6GHz, 14 Cores, 20 Threads, 24MB Cache, 65W Intel Core i5-13500TE: 1.3~4.5GHz, 14 Cores, 20 Threads, 24MB Cache, 35W Intel Core i7-12700E: 2.1~4.8GHz, 12 Cores, 20 Threads, 25MB Cache, 65W Intel Core i7-12700TE: 1.4~4.6GHz, 12 Cores, 20 Threads, 25MB Cache, 35W Intel Core i7-13700E: 1.9~5.1GHz, 16 Cores, 24 Threads, 30MB Cache, 65W Intel Core i7-13700TE: 1.1~4.8GHz, 16 Cores, 24 Threads, 30MB Cache, 35W Intel Core i9-12900E: 2.3~5.0GHz, 16 Cores, 24 Threads, 30MB Cache, 65W Intel Core i9-12900TE: 1.1~4.8GHz, 16 Cores, 24 Threads, 30MB Cache, 35W Intel Core i9-13900E: 1.8~5.2GHz, 24 Cores, 32 Threads, 36MB Cache, 65W Intel Core i9-13900TE: 1.0~5.0GHz, 24 Cores, 32 Threads, 36MB Cache, 35W |
| Performance Cores | 4 Cores 6 Cores 12 Cores 14 Cores 16 Cores 20 Cores 24 Cores |
| GPU / AI Accelerator | Discrete GPU (PCIe) |
| Supported GPUs | RTX 4000 SFF Ada RTX 4500 Ada RTX 5000 Ada RTX A1000 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 PRO 4500 Blackwell: 10496 CUDA Cores, 32GB GDDR7 ECC, 200W 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 | 54–1,617 TOPS |
| GPU Family | NVIDIA RTX Ada NVIDIA RTX Ampere NVIDIA RTX PRO Blackwell |
| GPU Architecture | NVIDIA Ada Lovelace NVIDIA Blackwell NVIDIA Ampere |
| Memory | 2x DDR4 3200MHz SO-DIMM Slots, 64GB |
| Chipset | Intel Q670E |
| PCIe Gen Support | PCIe 4.0 |
| Secure Crypto Processor | TPM 2.0 (Trusted Platform Module) |
| Operating System | Linux Windows 11 |
| Graphics | |
| Integrated GPU | Intel UHD Series |
| Multi Display Support | Triple Display Support |
| Display Outputs | 1x HDMI 2x Display Port |
| Audio | |
| Interface | Line-Out Mic-In |
| I/O | |
| Ethernet | 3x Ethernet Ports |
| 3x 2.5 GbE LAN [RJ45] | |
| LAN Controllers | Intel I226LM Intel I226V |
| USB | 8x USB Ports |
| 2x USB 3.2 Gen 1 [Type A] 6x USB 3.2 Gen 2 [Type A] | |
| Serial | 4x Serial Ports |
| 2x RS232 [Board] 2x RS232/422/485 [DB9] | |
| Expansion | |
| M.2 | 3x M.2 Expansion Slots |
| 1x M.2 B-Key [PCIe x1/USB/SIM] [3042] 1x M.2 E-Key [PCIe x1/USB 2.0] [2230] 1x M.2 M-Key [PCIe x4] [2242/2280] | |
| PCIe | See Variant Specifications |
| SIM Slots | 1x SIM Slots |
| Wireless Connectivity | Optional 4G Modem Optional 5G Modem Optional WiFi/Bluetooth |
| Storage | |
| Storage | 2x 2.5" HDD/SSD 2x M.2 SSD |
| NVMe | NVMe SSD Support |
| Hot Swap SSD Support | Hot Swappable SSD Support |
| RAID | RAID 0 (Striping) RAID 1 (Mirroring) |
| Power | |
| Power Input | See Variant Specifications |
| Power Support Modes | AT: PWR on Input ATX: Press Button to Power |
| Ignition Sensing | Supports Ignition Control |
| Environmental Conditions | |
| Thermal Dissipation | Onboard Fan |
| Operating Temperature | 0°C to 35°C [32°F to 95°F] |
| Storage Temperature | -20°C to 70°C [-4°F to 158°F] |
| Humidity | 5% - 95% (Non-condensing) |
| Certification | IEC 62368-1 CB CE FCC IC (ICES-003) UKCA UL 62368-1 |
| Mechanical Properties | |
| Weight | 4.0 Kg (8.8 Lbs) |
| Dimensions | 483mm x 480mm x 44mm (19.02" x 18.90" x 1.73") |
| Mounting Options | 19" Rack Mount |
No specifications match your search.
See product variants.
LLM-1U-RPL Variants
Premio LLM-1U-RPL-2E8-600W-DC Intel 12th to 14th Gen Core 1U Edge AI Server with Dual PCIe x8 Slots and Redundant DC Power
LLM-1U-RPL with two PCIe x8 Gen4 slots and redundant 600W DC power
| Overview | |
|---|---|
| Brand & Model | Premio LLM-1U-RPL-2E8-600W-DC |
| Expansion | |
| PCIe | 2x PCIe Slots |
| 2x PCIe [x8 Slot] [Gen4] | |
| Power | |
| Power Input | 36-72V DC Input |
Premio LLM-1U-RPL-2E8-600W-AC Intel Core i9/i7/i5 14th Gen 1U Edge AI Server with Dual PCIe x8 Slots and Redundant AC Power
LLM-1U-RPL with two PCIe x8 Gen4 slots and redundant 600W AC power
| Overview | |
|---|---|
| Brand & Model | Premio LLM-1U-RPL-2E8-600W-AC |
| Expansion | |
| PCIe | 2x PCIe Slots |
| 2x PCIe [x8 Slot] [Gen4] | |
| Power | |
| Power Input | 115-230V AC [IEC C14], AC Power Supply Included |
Premio LLM-1U-RPL-1E16-600W-DC Intel Raptor Lake 1U Edge AI Server with PCIe x16 GPU Slot and Redundant DC Power
LLM-1U-RPL with one PCIe x16 Gen4 GPU slot and redundant 600W DC power
| Overview | |
|---|---|
| Brand & Model | Premio LLM-1U-RPL-1E16-600W-DC |
| Expansion | |
| PCIe | 1x PCIe Slots |
| 1x PCIe [x16 Slot] [x16 Signal] [Gen4] | |
| Power | |
| Power Input | 36-72V DC Input |
| Performance | |
| Number of GPUs | Single GPU Support |
Premio LLM-1U-RPL-1E16-600W-AC Intel 14th Gen Core 1U Edge AI Server with PCIe x16 GPU Slot and Redundant AC Power
LLM-1U-RPL with one PCIe x16 Gen4 GPU slot and redundant 600W AC power
| Overview | |
|---|---|
| Brand & Model | Premio LLM-1U-RPL-1E16-600W-AC |
| Expansion | |
| PCIe | 1x PCIe Slots |
| 1x PCIe [x16 Slot] [x16 Signal] [Gen4] | |
| Power | |
| Power Input | 115-230V AC [IEC C14], AC Power Supply Included |
| Performance | |
| Number of GPUs | Single GPU Support |
No related media available for this product series.
Official Premio USA Distributor
Things Embedded is an official Premio USA distributor, and we supply the LLM-1U-RPL series configured and tested, with DDR4 memory, SATA and NVMe storage, the NVIDIA RTX GPU card and the Windows 11 or Linux image fitted before it ships. Within the Premio range, the LLM-2U-AM5 moves to AMD Ryzen 9000 and EPYC 4005 processors in 2U with 10GbE SFP+ and two PCIe x16 Gen5 slots, and the LLM-3U-AM5 takes the same AMD board in 3U with a 3.5" drive bay. If you are unsure whether one x16 slot or two x8 slots suits your cards, or whether your rack needs AC or -48 V DC supplies, our team can help you choose.
Across our range, the LLM-1U-RPL series sits with our rack mount servers, our NVIDIA RTX PRO Blackwell computers and our edge AI 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.