Product features
CPU & GPU
- Processor: 1x NVIDIA Grace 72-core Neoverse V2 CPU (ARM-based)
- GPU: 1x NVIDIA Blackwell Ultra GPU
- MIG: Multi-instance GPU for up to 7 MIGs
- optional: 1x dedicated NVIDIA Blackwell GPU for graphics rendering, e.g. RTX Pro 2000 Blackwell
RAM
- total coherent memory: 748GB, linked via NVLink ®-C2C, at 900 GB/s interconnect bandwidth
- CPU memory: 496GB ECC LPDDR5X, 396 GB/s memory bandwidth
- GPU memory: 252GB ECC HBM3e, 7.1 TB/s memory bandwidth
Networking
- Dual-port QSFP112 400GbE LAN via NVIDIA ConnectX-8 SuperNIC (= 800 Gbit/s bandwidth total)
- 1x RJ45 1GbE Dedicated BMC LAN port
- 1x RJ45 10GbE LAN port
Storage
- 4x M.2 PCIe 5.0 x4 NVMe (M-key 2280)
- populated with 3x 2TB Phison SSDs - configurable
PCIe Slots
- 1x PCIe Gen 5 x16 FHFL double-width
- 2x PCIe Gen 5 x8 (in x16) FHHL
- 1x M.2 PCIe 5.0 x4 slot (E-Key 2230))
Front IO Ports and Connectors
- 2x USB 3.1 Type A
- power on/off button
- reset button
- HDD activity LED
- Power status LED
Rear IO Ports and Connectors
- 4x USB 3.1 Gen2 Type A (10 Gbit/s)
- 1x mini-DP (video port)
- audio ports (3 audio jacks)
OS & security
- security hardware: Silicon Root of Trust (RoT) – NIST 800-193 Compliant
- BIOS type: AMI 64MB SPI Flash EEPROM
- OS: Ubuntu 24.04 LTS with NVIDIA AI Developer Tools
- pre-installed with essential CUDA-X™ libraries
IT manageability and enterprise features
- out-of-band telemetry via BMC
- Redfish API support
- NVIDIA Data Center GPU Manager
- visibility, monitoring, remote management capabilities
- hardware root of trust
- enterprise secure boot
Dimensions, weight, form factor
- Form factor: 5U rack-mountable desktop tower
- height: 8.6" (218.4 mm)
- width: 17.9" (454.7 mm)
- depth: 27.6" (701 mm)
- package: 25.8" (H) x 15.3" (W) x 37.6" (D)
- gross weight: 112.4 lbs (51 kg)
- net weight: 88 lbs (40 kg)
System cooling
- cooling system: closed-loop liquid cooling (suitable for office use)
- liquid cooling: Direct to Chip (D2C) Cold Plate
- 2 x 120mm Fans
- 1x 80mm Fan
- 1x 60mm Fan
- 1x 40mm Fan
Power supply
- power supply: 1x 1600W Titanium Level (94%) power supply, 100 - 240V
- power input @ 1300W: 100-114Vac / 50-60Hz
- power input @ 1600W: 115-240Vac / 50-60Hz
Misc
- color: black front + black body
- operating temperature: 10°C to 25°C (50°F to 77°F)
- storage temperature: -40°C to 60°C (-40°F to 140°F)
- operating relative humidity: 8% to 90% (non-condensing)
- storage relative humidity: 5% to 95% (non-condensing)
AI performance
- FP4 Tensor core: 20 PFLOPS / 15 PFLOPS without sparsity
- FP8 / FP6 Tensor core: 10 PFLOPS
- Int8 Tensor Core: 330 TOPS
- FP16/BF16 Tensor Core: 5 PFLOPS
- TF32 Tensor Core: 2.5 PFLOPS
- FP32: 80 TFLOPS
- FP64 / FP64 Tensor Core: 1.3 TFLOPS
Product description
The Supermicro Super AI Station ARS-511GD-NB-LCC is an NVIDIA DGX Station based on the GB300 superchip. It can be used for running local AI applications for development and production purposes.
Example AI applications include LLM inference for frontier models of up to 1 Trillion parameters, scientific workloads (e.g. BioNeMo), finetuning models, hosting AI agents, and running RAGs for AI-enhanced document workflows. In particular it is well-suited to run MoE (mixture of experts) models.
Thanks to its MIG feature and its massive memory throughput it can be run headless to support several colleagues in a local workgroup.
Compared to server systems, or heavy multi-GPU systems, it runs cooler and quieter, and is uniquely suited for office use. Its server-grade management features, such as the integrated BMC, the Redfish API support, and enterprise secure boot allow to integrate it into a corporate IT management landscape.
Two ARS-511GD-NB-LCC DGX Stations can be joined using the Dual-port QSFP112 400GbE LAN to serve even bigger models, increase precision, or general model performance.
Supermicro offers a special feature: You can use their DGX Station version at your desk, or mount it into a rack with the optional Supermicro DGX Station rack mounting kit.
A 48U sample rack configuration could include 8x the Supermicro ARS-511GD-NB-LCC Super AI Station (this product), two storage servers, two Ethernet switches, and would use 18kW of operating power.
A separately obtainable NVIDIA AI Enterprise software license provides a suite of software tools, libraries, and frameworks to fast-track your AI deployment on the Supermicro DGX station.
Datasheets, manuals and additional downloads
Lead time & purchase
This product is available on pre-order with a current lead time of about 4-6 weeks. Contact us to purchase it.
Additional SKUs and codes
- ARS-511GD-NB-LCC
- ARS-511GD-NB-LCC-01-G2 = Gold Series version with pre-configured components
- Chassis model: CSE-759TS-R0CNBP
- Motherboard: Super GPU-NVGB300-WSHPM