AI Server with 6 AMD MI60 GPUs | 64 Threads | 128GB RAM | 192GB VRAM | Turn Key For Sale
When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.
AI Server with 6 AMD MI60 GPUs | 64 Threads | 128GB RAM | 192GB VRAM | Turn Key:
$8999.00
Item: Supermicro X10DRG-OT+ AI Server (4U Rackmount)
Condition: Used, Rigorously Tested for Reliability and Optimized for AI Inference Workloads
GPU's ARE INCLUDED
Private Turn-Key AI Inference Server - Host Local LLMs with the highest Performance per Dollar & Privacy
Fully Configured & Ready-to-Use: Ubuntu, AMD ROCm, Ollama, Open WebUI Installed
Server Specifications:
- 2 Intel E5-2697A v4 Xeon 16-Core Processors at 2.6 GHz ( 64 Threads Total)
- 128 GB DDR4 ECC RAM
- 6 AMD Instinct MI60 32GB GPUs ( 192 GB VRAM )
- 1 AMD RX550 Display Card ( Used for local console video out only )
- Dual Intel X540 10GBase-T Ports for Uninterrupted Connectivity
- Storage Configuration: 1 - 2TB NVME and 2 - 480GB Sata SSDs
- Dimensions (with handles): 30" (L) x 7" (H) x 19" (W)
Software and OS:
Pre-installed with Ubuntu, AMD ROCm, Ollama, and Open WebUI
Comes with multiple LLM Models pre-configured and the ability to easily add more.
Comprehensive Documentation Included for Immediate Deployment of AI Inference Workloads
Why Choose Local Hosting over Public LLMs?
- Enhanced Security: Keep your data entirely private, away from public cloud risks.
- Full Control: Manage and customize your AI environment as per your requirements.
- Compliance: Ensure adherence to stringent data protection regulations.
Additional Details:
- I have meticulously tested these servers, and optimized them for AI inference workloads.
- I also will include a comprehensive getting-started guide and remain available for support to ensure you are able to get up and running quickly.
- I have also included a System Recovery on the second 480 GB SSD (/dev/sdb2) in case you need to restore the original configuration.