| Best for | One developer or researcher, or a small team, with the NVIDIA stack on the desk. NVIDIA DGX Spark and the EMARQUE AI Work 100. | NVIDIA DGX Station, a Grace Blackwell Ultra machine that installs beside a desk, and the EMARQUE AI PRO 500, four RTX PRO 6000 GPUs on a Threadripper PRO workstation platform in a 5U chassis. | Single-node rackmount platforms: the EMARQUE AI Server (six or eight GPUs) and AI HGX B300, plus NVIDIA DGX B200 and DGX B300. | NVIDIA GB300 NVL72 and Vera Rubin NVL72, where a whole rack behaves as one accelerator. We source these through NVIDIA's OEM partners and coordinate the install. |
|---|
| Model size | DGX Spark: up to 200B parameters (NVIDIA figure). AI Work 100: 70B class at 4-bit on one 48 or 96 GB card, at 16-bit across two 96 GB cards. | DGX Station: 748 GB of coherent memory (252 GB HBM3e + 496 GB LPDDR5X), so large models run on one machine. AI PRO 500: 384 GB of GPU memory across four cards | 70B-class serving, fine-tuning, or several models side by side | Training and serving the largest models; 20 TB of HBM3e per GB300 NVL72 rack |
|---|
| Form factor | Compact desktop (DGX Spark) or desk-side tower (AI Work 100) | Desk-side tower (DGX Station) or 5U rackmount (AI PRO 500) | 6.5U to 10U rackmount | One rack as a single accelerator (NVL72) |
|---|
| Cooling | Office air, no special HVAC | DGX Station: cooled inside the unit, in a normal office. AI PRO 500: air-cooled, in a rack | Air-cooled, in a server room or with in-row cooling. The AI HGX Rubin is liquid-cooled | Direct-to-chip liquid, with a coolant distribution unit |
|---|
| Power | DGX Spark 240 W; the AI Work 100 runs from a standard wall outlet | DGX Station 1,600 W, on a 20 A circuit (NVIDIA figure); AI PRO 500 on a 3,000 W supply | Up to about 14 to 14.5 kW for an eight-GPU HGX or DGX system (NVIDIA figures for DGX B300); 9,600 W of supplies in the eight-GPU AI Server | Confirmed with the OEM at design. NVIDIA publishes no per-rack figure. |
|---|
| When to step up | The model no longer fits the memory you have, or a department needs it rather than one desk. | You need more than one machine, or it has to live in a rack with the rest of IT. | One node is no longer enough and the work has to spread across a rack of GPUs on one NVLink fabric. | More racks on the same fabric. |
|---|