- Joined
- Oct 9, 2007
- Messages
- 47,814 (7.40/day)
- Location
- Dublin, Ireland
| System Name | RBMK-1000 |
|---|---|
| Processor | AMD Ryzen 7 5700G |
| Motherboard | Gigabyte B550 AORUS Elite V2 |
| Cooling | DeepCool Gammax L240 V2 |
| Memory | 2x 16GB DDR4-3200 |
| Video Card(s) | Galax RTX 4070 Ti EX |
| Storage | Samsung 990 1TB |
| Display(s) | BenQ 1440p 60 Hz 27-inch |
| Case | Corsair Carbide 100R |
| Audio Device(s) | ASUS SupremeFX S1220A |
| Power Supply | Cooler Master MWE Gold 650W |
| Mouse | ASUS ROG Strix Impact |
| Keyboard | Gamdias Hermes E2 |
| Software | Windows 11 Pro |
Leading provider of advanced AI solutions AAEON has released a new addition to its AI Inference Server product line, the MAXER-5100 - the world's first 8L AI inference server equipped with two integrated GPUs. The MAXER-5100's default model comes with the 24 core, 32 thread 14th Generation Intel Core i9 processor 14900K and two onboard NVIDIA RTX 2000 Ada GPUs. Meanwhile, a barebone SKU is available, accommodating up to 65 W CPUs from across the 12th, 13th, and 14th Generation Intel Core processor lines as well as PCIe slots for other compatible GPUs, per project need.
Given the processing power and AI performance the system offers, the MAXER-5100 is primarily positioned as a central server for the management of multiple edge devices, particularly with its Certificate Authority (CA) support granting additional security for smart infrastructure, healthcare, and advanced manufacturing applications. Moreover, the MAXER-5100's use of a zero-trust secure tunnel and onboard TPM 2.0 allows for encrypted data transmission between the server and multiple edge devices, as well implement over-the-air updates and remote diagnostics.
The MAXER-5100 can host up to 128 GB of DDR5 storage via four DIMM slots, while storage is scalable and customizable through a combination of both 2.5" SSD and 3.5" HDD bays and an M.2 2280/2242 M-Key slot for either PCIe Gen 4 or additional SATA modules, where greater capacity is needed for solutions running inferencing engines for AI pipelines alongside large datasets. With this combination of high-speed storage and memory support, the MAXER-5100 can also be seen as a platform for AI model fine-tuning or running LLMs on the edge, particularly given its dual GPU setup.
In terms of I/O, the system hosts dual RJ-45 ports for both 2.5GbE and 1GbE LAN, a total of four USB ports, and a DB-9 port for RS-232/422/485 & RI/5 V/12 V signals. For display, the MAXER-5100 provides HDMI, VGA, and DP 1.4 outputs.
With respect to expansion, the MAXER-5100's M.2 2280/2242 M-Key and HDD bays are joined by one 8-lane PCIe Gen 4 slot and two PCIe Gen 3 slots (one 4-lane and one 1-lane), as well as an M.2 2230 E-Key that can be populated with modules for Wi-Fi, 5G, or other wireless communication modules.
At just 305 mm x 95 mm x 276 mm, the MAXER-5100 is remarkably compact. Despite this, the system delivers the airflow and heat management required to operate at full capacity due to a custom-designed thermal solution made up of both CPU and system fans engineered to produce minimal noise.
For more information and detailed specifications for the MAXER-5100.
View at TechPowerUp Main Site
Given the processing power and AI performance the system offers, the MAXER-5100 is primarily positioned as a central server for the management of multiple edge devices, particularly with its Certificate Authority (CA) support granting additional security for smart infrastructure, healthcare, and advanced manufacturing applications. Moreover, the MAXER-5100's use of a zero-trust secure tunnel and onboard TPM 2.0 allows for encrypted data transmission between the server and multiple edge devices, as well implement over-the-air updates and remote diagnostics.
The MAXER-5100 can host up to 128 GB of DDR5 storage via four DIMM slots, while storage is scalable and customizable through a combination of both 2.5" SSD and 3.5" HDD bays and an M.2 2280/2242 M-Key slot for either PCIe Gen 4 or additional SATA modules, where greater capacity is needed for solutions running inferencing engines for AI pipelines alongside large datasets. With this combination of high-speed storage and memory support, the MAXER-5100 can also be seen as a platform for AI model fine-tuning or running LLMs on the edge, particularly given its dual GPU setup.
In terms of I/O, the system hosts dual RJ-45 ports for both 2.5GbE and 1GbE LAN, a total of four USB ports, and a DB-9 port for RS-232/422/485 & RI/5 V/12 V signals. For display, the MAXER-5100 provides HDMI, VGA, and DP 1.4 outputs.
With respect to expansion, the MAXER-5100's M.2 2280/2242 M-Key and HDD bays are joined by one 8-lane PCIe Gen 4 slot and two PCIe Gen 3 slots (one 4-lane and one 1-lane), as well as an M.2 2230 E-Key that can be populated with modules for Wi-Fi, 5G, or other wireless communication modules.
At just 305 mm x 95 mm x 276 mm, the MAXER-5100 is remarkably compact. Despite this, the system delivers the airflow and heat management required to operate at full capacity due to a custom-designed thermal solution made up of both CPU and system fans engineered to produce minimal noise.
For more information and detailed specifications for the MAXER-5100.
View at TechPowerUp Main Site
Hope that flex PSU has a quite 40mill screamer....