Product features
CPU & GPU
- Processor: 1x NVIDIA Grace ™ 72-core Neoverse V2 CPU (ARM-based) - 270W, up to 3 GHz
- GPU: 1x NVIDIA Blackwell Ultra GPU
- MIG: Multi-instance GPU for up to 7 MIGs
Dedicated GPU
- 1x NVIDIA RTX Pro 2000 Blackwell GPU for graphics rendering
- 4x mini DisplayPort outputs
- 16GB GDDR7
- PCIe 5
- 75W power consumption
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 (SOCAMM, 6400 MT/s)
- 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 4.0 x4 NVMe (M-key 2280), up to 64 Gbps
- populated with 4x 4TB Gen4 SSDs, SED ready - configurable (up to 4 TB each)
PCIe Slots
- 1x PCIe Gen 5 x16 FHFL double-width, for GPUs
- 2x PCIe Gen 5 x8 (in x16) FHHL
- 1x M.2 PCIe 2.0 x1 slot (E-Key 2230))
Top IO Ports and Connectors
- 2x USB 3.2 Gen2 port (Type-C, 10 Gbps)
- 2x USB 3.2 Gen1 ports (Type-A, 10 Gbps)
- 1x power button
Rear IO Ports and Connectors
- 4x USB 3.2 Gen2 ports (Type-A, 10 Gbit/s)
- 4x mini-DP (supported through discrete GPU)
- 2x QSFP112 (400 Gbps) ports
- 1x RJ45 port 10 Gbit/s Ethernet (AQC113)
- 1x RJ45 management port 1 Gbit/s Ethernet (AQC113)
- 1 x audio input / microphone - 3.5 mm, 2 stack
- 1x line-in audio port - 3.5 mm, 2 stack
- 1x line-out audio port - 3.5 mm, 2 stack
- Kensington security-cable slot (Kensington Lock)
OS & security
- OS: Ubuntu 24.04 LTS with NVIDIA AI Developer Tools
- pre-installed with essential CUDA-X™ libraries
- Trusted Platform Module (TPM) 2.0 discrete
- FIPS 140-2 certification for TPM
- FIPS 140-3 certification for TPM
- TCG certification for TPM (Trusted Computing Group)
- 1x Kensington security-cable slot
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: desktop tower
- height: 569 mm / 22.40 inch
- width: 231.6 mm / 9.12 inch
- depth: 610.50 mm / 24.04 inch
- weight: starting at 38,89 kg (85.75 lb), depends on configuration
System cooling
- cooling system: closed-loop liquid cooling (suitable for office use)
- Dell MaxCool technology with smart cold plate design and dual heat exchangers
- redundant pump system
- quieter, more reliable performance to sustain peak power without thermal throttling
Power supply
- power supply: 1x 1600W Titanium power supply, 90 - 264VAC, 47Hz - 63Hz
- C19 inlet
- max input current
- 15 A @ 100 VAC, 1300W
- 16 A @ 115 VAC, 1600W
- 8 A @ 240 VAC, 1600W
- 12V total output power: 1600W, 131.15A
- 5V/3.3V maximum combined power: 135W
Misc
- Audio: Realtek® ALC4080 Audio Codec
- main chassis: Dell standard black powder-coated metal
- Left and right door: Magnetite painted metal
- Top, front, and bottom cover: Magnetite painted resin
- no wireless connection
- operating temperature: 0°C to 50°C (32°F -122°F)
- storage temperature: -40°C to 70°C (-40°F to 158°F)
- operating relative humidity: 20% - 80% (non-condensing)
- storage relative humidity: 5% - 95% (non-condensing)
- Vibration (maximum): 0.52 GRMS operating 2.0 GRMS storage
- Shock (maximum) 40 G operating, 105 G storage
- altitude range operating: -15.2m - 3048 m (-49.87ft - 10.000 ft)
- altitude range storage: -15.2m - 10.668m (-49.87ft - 35.000 ft)
-
ENV0424 compliant
- Airborne contaminant level: G1 as defined by ISA-S71.04-1985
packing content:
- 1 x Dell Pro Max with GB300 (FCT6263) AI Supercomputer (NVIDIA DGX Station GB300)
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 Dell Pro Max with GB300 (FCT6263) AI Supercomputer is an NVIDIA DGX Station based on the GB300 Grace™ Blackwell 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 Dell Pro Max with GB300 FCT6263 DGX Stations can be joined using the Dual-port QSFP112 400GbE LAN to serve even bigger models, increase precision, or general model performance.
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 Dell Pro Max with GB300.
Dell support service levels
Dell offers a variety of support service levels
-
1Y Basic Hardware Service with onsite service after remote diagnosis
-
2Y Basic Hardware Service with onsite service after remote diagnosis
-
3Y Basic Hardware Service with onsite service after remote diagnosis
-
1Y ProSupport with Next Business Day Onsite Service
-
2Y ProSupport with Next Business Day Onsite Service
-
3Y ProSupport with Next Business Day Onsite Service
-
1Y ProSupport Plus for Client with Next Business Day Onsite Service
-
2Y ProSupport Plus for Client with Next Business Day Onsite Service
-
3Y ProSupport Plus for Client with Next Business Day Onsite Service
-
1Y Keep Your Hard Drive
-
2Y Keep Your Hard Drive
- 3Y Keep Your Hard Drive
Datasheets, manuals and additional downloads
- Dell Pro Max with GB300 FCT6263 setup and specificatons (PDF)
- Dell Pro Max with GB300 FCT6263 Service Manual (PDF)
- DELL Pro Max with GB300 FCT6263 support page
- DELL Pro Max with GB300 Ubuntu 24.04 LTS with NVIDIA AI Developer Tools recovery ISO image (9.62 GB)
Lead time & purchase
This product is available on pre-order with a current lead time of about 4-12 weeks. Contact us to purchase it.
Additional SKUs and codes
- model number: FCT6263







