Supermicro AMD Instinct GPU Systems
GPU servers built on AMD Instinct MI350-series and MI325X accelerators with AMD EPYC processors, air- or liquid-cooled, for large-scale AI training and inference clusters.
Find alternatives to Supermicro AMD Instinct GPU Systems
What it does
- Server systems
- AI compute hardware
- Model training
- Model inference
Sources
- Pricing
-
Read the page: no price is published.
- Description
-
Company disclosure · 11 Nov 2026
"Supermicro unleashes the power of large-scale infrastructure with a server built with our proven AI building-block system and powered by 5th Gen AMD EPYC™ processors and AMD Instinct™ MI350 series GPUs".
- What it does
-
Company disclosure · 11 Nov 2026
"our proven AI building-block system"; "each GPU for massive AI clusters".
- Sold within
-
Read the page: no parent offering or bundle is named; it is a family of separately configured systems.
- Name
-
Company disclosure · 11 Nov 2026
Page title "Supermicro Systems with AMD Instinct™ Series GPUs".
- URL
-
Company disclosure · 11 Nov 2026
Supermicro's own page for the family.
- Deployment
-
Company disclosure · 11 Nov 2026
Servers the buyer installs in its own data centre or site.
Also from Super Micro Computer
-
Supermicro AI SuperCluster Infrastructure service
Turnkey liquid- or air-cooled AI clusters of NVIDIA GPU servers, built, tested and delivered as full racks for model training and inference.
-
Supermicro Super AI Station Hardware
Liquid-cooled deskside or 5U rack AI system built on one NVIDIA GB300 superchip, with 748GB of coherent memory and 20 PFLOPS of FP4, for running, fine-tuning and developing AI models and agents on premises.
-
Supermicro Data Center Building Block Solutions (DCBBS) Infrastructure service
Supermicro's end-to-end AI data-centre offering that combines its GPU systems, storage, in-rack and in-row liquid cooling, power, networking, site cooling towers, management software and on-site deployment services into one validated build.
-
SuperCloud Developer Console (SDX) Infrastructure service
Multi-tenant developer console for Supermicro GPU clusters that provisions GPU slices and ML pipelines in one click for training, fine-tuning, inference and benchmarking, with quotas, RBAC and GPU-utilisation monitoring.
-
Supermicro NVIDIA Vera Rubin NVL72 Infrastructure service
Liquid-cooled rack-scale system on NVIDIA's Vera Rubin NVL72 platform for agentic AI inference and training, delivered with Supermicro's DLC-2 direct liquid cooling and building-block data centre stack.
-
Eight-accelerator AI training and inference server on Intel Gaudi 3, part of Supermicro's Intel GPU line beside Data Center GPU Flex media servers.
-
Fanless edge computer on NVIDIA's Jetson Orin NX module for running AI inference on site in retail, manufacturing and logistics, up to 157 TOPS.
-
NVIDIA-Certified GPU servers on H100 and H200 Tensor Core GPUs, from single systems to unified AI training clusters -- the generation before Blackwell.
-
Supermicro NVIDIA PCIe GPU Systems Hardware
Servers for PCIe GPUs such as NVIDIA RTX PRO 6000 Blackwell Server Edition and H200 NVL, for LLM inference and fine-tuning alongside graphics, rendering and virtualisation.
Open Super Micro Computer in the directory
Something wrong here? Send a correction — quote this product id: supermicro-amd-instinct-systems.