DGX Spark
Local LLM inference, development, selected fine-tuning
- Memory
- 128 GB coherent unified memory
- Storage
- 4 TB NVMe M.2
- Price
- $4,699.00
Availability Listed; verify current stock and region
Explore partner offerProduct catalog
Compare local AI systems using published specifications, dated pricing notes, and an explicit distinction between official listings and approved partner links.
Quick comparison
Prices, availability, and specifications can change. Use this table to choose what to verify in a current vendor quote.
| Specification | DGX Spark | ThinkStation PGX | Ascent GX10 | Dell Pro Max with GB10 |
|---|---|---|---|---|
| Manufacturer | NVIDIA | Lenovo | ASUS | Dell |
| Product family | GB10 Grace Blackwell | GB10 Grace Blackwell | GB10 Grace Blackwell | GB10 Grace Blackwell |
| Processor | 20-core Arm CPU in GB10 Grace Blackwell Superchip | 20-core Arm CPU | 20-core Arm CPU in GB10 Superchip | 20-core Arm CPU in GB10 Superchip |
| GPU | NVIDIA Blackwell GPU | NVIDIA GB10 Grace Blackwell GPU | NVIDIA GB10 Grace Blackwell GPU | NVIDIA GB10 Grace Blackwell GPU |
| Memory | 128 GB coherent unified memory | 128 GB unified memory | 128 GB unified memory | 128 GB LPDDR5X unified memory |
| Storage | 4 TB NVMe M.2 | 1 TB NVMe | 4 TB NVMe listed configuration | 1 TB, 2 TB, or selected 4 TB M.2 NVMe configurations |
| Operating system | NVIDIA DGX OS | — | — | NVIDIA DGX OS 7 |
| Listed price | $4,699.00 | Quote dependent | $3,999.00 | $5,654.39 |
| Link | Partner offer ↗ | Official listing ↗ | Official listing ↗ | Official listing ↗ |
The table includes four frequently compared GB10 systems. A partner link appears only when an approved affiliate URL exists; otherwise the link goes to the manufacturer's official listing.
Full catalog
Every card keeps unknown values explicit and links to a current official source or an approved partner destination.
Local LLM inference, development, selected fine-tuning
Availability Listed; verify current stock and region
Explore partner offerShared local development and inference
Availability Order now; contact an NVIDIA partner
Explore partner offerEnterprise multi-GPU training and high-throughput inference
Availability Quote and OEM dependent
Explore partner offerCUDA local inference and development
Availability OEM and region dependent
View official listingLocal LLM inference and AI development
Availability Verify US configuration and stock
View official listingLocal AI development and inference
Availability Listed for purchase in the US; configuration and region dependent
View official listingLocal LLM development and inference
Availability Region and configuration dependent
View official listingLocal AI development and inference
Availability Region and configuration dependent
View official listingSome NVIDIA products in this catalog use a marked Aradia referral link. Eligible purchases may compensate AI Compute Scout. Unapproved merchants remain official links only. Read the full disclosure.