
Apple
Apple Mac Studio (M5 Ultra)
- GPU model
- 64-core GPU (80-core available)
- CPU cores (total)
- 30
- CPU model
- Apple M5 Ultra
₹6,29,900
Backorder

NVIDIA · DGX Station — GB300 Grace Blackwell Ultra Desktop Superchip
Deskside AI supercomputer: Blackwell Ultra GPU with 252 GB HBM3e at 7.1 TB/s, 72-core Grace CPU with 496 GB LPDDR5X, 800 Gb/s ConnectX-8 networking.
₹1,67,47,713
Inclusive of 18% GST. Invoice details confirmed with your order.
NVIDIA DGX Station is a deskside AI supercomputer built on the GB300 Grace Blackwell Ultra Desktop Superchip: one Blackwell Ultra GPU with 252 GB of HBM3e ECC memory at 7.1 TB/s, connected over 900 GB/s NVLink-C2C to a 72-core Grace CPU with 496 GB of LPDDR5X ECC memory. A ConnectX-8 SuperNIC provides up to 800 Gb/s networking, and one additional NVIDIA RTX PRO Blackwell GPU can be fitted for visualisation and simulation. Total system power is 1,600 W on a 20 A circuit.
DGX Station is built by NVIDIA's system partners. Price is based on the starting price an NVIDIA partner (Exxact, Valence VWS-158270643) publishes for its DGX Station build (USD); options are quoted on request. Specifications are NVIDIA's published figures (Tensor Core figures with sparsity unless noted).
| GPU | 1x NVIDIA Blackwell Ultra | Vendor-reported |
|---|---|---|
| GPUs | 1 | Vendor-reported |
| GPU memory | 252 GB | Vendor-reported |
| GPU memory type | HBM3e ECC | Vendor-reported |
| GPU memory bandwidth | 7100 GB/s | Vendor-reported |
| Multi-Instance GPU | Up to 7 instances | Vendor-reported |
| CPU | 1x NVIDIA Grace 72-core Neoverse V2 | Vendor-reported |
|---|---|---|
| CPU cores | 72 | Vendor-reported |
| CPU memory | 496 GB | Vendor-reported |
|---|---|---|
| CPU memory type | LPDDR5X ECC, 396 GB/s | Vendor-reported |
| ECC memory | Yes | Vendor-reported |
| CPU–GPU interconnect | NVLink-C2C, 900 GB/s | Vendor-reported |
|---|---|---|
| Networking (peak) | 800 Gb/s | Vendor-reported |
| Network adapter | NVIDIA ConnectX-8 SuperNIC (Ethernet) | Vendor-reported |
| Ethernet ports | 2 | Vendor-reported |
| Port type | 2x QSFP112 (400 Gb/s per port) | Vendor-reported |
| FP4 Tensor Core (sparse | dense) | 20 | 15 PFLOPS | Vendor-reported |
|---|---|---|
| FP8 / FP6 Tensor Core (sparse) | 10 PFLOPS | Vendor-reported |
| FP16 / BF16 Tensor Core (sparse) | 5 PFLOPS | Vendor-reported |
| FP32 | 80 TFLOPS | Vendor-reported |
| FP64 / FP64 Tensor Core | 1.3 TFLOPS | Vendor-reported |
| Storage slots (M.2 Gen 5) | 4 | Vendor-reported |
|---|
| Total system power | 1600 W | Vendor-reported |
|---|---|---|
| Electrical circuit | 20 A circuit required | Vendor-reported |
| Operating system | Ubuntu with NVIDIA AI Developer Tools | Vendor-reported |
|---|
No measured benchmarks are published for this product yet. GIRIVON does not publish estimated figures as benchmarks; use the workload performance estimator with your own measurements.
The compatibility engine validates this product against other components using its structured attributes (17 recorded).
Manufacturer warranty applies. For installation, RMA and technical help, contact GIRIVON support.
No reviews yet. Reviews are moderated before publication.

Apple
₹6,29,900
Backorder

Supermicro
₹1,61,15,171
Built to order

Supermicro
₹16,84,640
Built to order