here!
I’m your shopping assistant for PC builds, upgrades, and everything tech.
Got questions? Ask away!
Start a conversation
HPE ProLiant Compute DL384 Gen12
- The HPE ProLiant Compute DL384 Gen12 provides outstanding coherent memory and memory bandwidth with up to two superchips per server with NVIDIA GH200 NVL2, allowing teams to run larger models faster and more cost-effectively. By partnering with NVIDIA, Hewlett Packard Enterprise continues to innovate with impressive infrastructure enhancements to help customers unlock scaled-out and accelerated computing for generative AI. With superchip performance in your AI factory, HPE ProLiant Compute DL384 Gen12 delivers superb performance per GPU in the HPE ProLiant portfolio. Simplify your approach to scaling with data demands and integrate accelerated compute to reliably prepare your data center for mixed workloads and retrieval-augmented generation (RAG) in the modern hybrid reality.
+
+
Reviews
See all Q & A 
Any questions? Ask CelesteSM will help you find out quickly.
Try me now
Warranty & Returns
Warranty, Returns, And Additional Information
Warranty
- Limited Warranty period (parts): 1 year
- Limited Warranty period (labor): 1 year
- Read full details
Return Policies
- Return for refund until: January 31, 2027
- Return for replacement until: January 31, 2027
- This item is covered by Newegg.com's Extended Holiday Return Policy.
- Read full return policy for details.
We want to ensure your holiday shopping this year is hassle-free. That’s why we’re automatically extending our return policies on almost every product! For purchases placed between November 1st, 2026 and December 31, 2026 you will have until January 31, 2027 to return your product.
Manufacturer Contact Info
- Manufacturer Product Page
- Manufacturer Website
- Support Phone: 1-888-269-4073
- Support Website
- View other products from HPE
LOADING...
The HPE ProLiant Compute DL384 Gen12 is a server barebones platform designed for enterprise generative AI, with support for up to two NVIDIA GH200 NVL2 superchips. It suits data-center teams running large models that need high coherent-memory bandwidth for accelerated computing.
Recommended For
- Enterprise AI teams serving large language models or retrieval-augmented generation (RAG) in a data center, especially when workloads benefit from high-bandwidth memory and low-latency CPU–GPU communication.
- Organizations fine-tuning or deploying larger generative AI models that want an integrated Grace CPU and Hopper GPU platform rather than a general-purpose rack server with separate processors and accelerators.
- Data-center operators building private or enterprise AI infrastructure who need to run interactive and batch LLM inference on a managed rack server; an audited STAC test evaluated both workload styles on the DL384 Gen12.
- HPC or other memory-intensive workload teams whose applications are suited to the Grace Hopper platform and can use its accelerated computing architecture.
Spec Summary
| Attribute | Value |
|---|---|
| Best For | AI and accelerated-computing workloads, including large-model development and mixed workloads |