Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Clear out junk files and repair common Windows errorsFree Scan →NVIDIA says its DGX Spark 64GB will be available Friday, October 23, 2026, from Acer, ASUS, Dell, Gigabyte, HP and MSI, with a starting price of $4,999. NVIDIA also says two 64GB systems connected over a 200 GbE fabric with Sync Cluster Assistant can pool 128GB of memory. That is a two-system cluster capacity, not a single physical computer or a guaranteed flat memory space for every application.
Launch date, price and manufacturers
NVIDIA’s October 2, 2026 announcement states: “DGX Spark 64GB is available from Acer, ASUS, Dell, Gigabyte, HP and MSI on Friday, Oct. 23, starting at $4,999.” The figure is NVIDIA’s announced starting price; current retailer inventory, transaction prices and exact SKU configurations are not established here. Read the announcement at NVIDIA’s blog.
| # | Preview | Product | Price | |
|---|---|---|---|---|
| 1 |
|
NVIDIA GX Spark - Founders Edition, W129251900 | $10,991.00 | Buy on Amazon |
| 2 |
|
Cooling Duct Compatible with NVIDIA DGX Spark GB10, 140mm Fan Mount Adapter | $27.99 | Buy on Amazon |
As an Amazon Associate I earn from qualifying purchases.
- Availability: Friday, October 23, 2026
- Starting price: $4,999, as announced by NVIDIA
- Named partners: Acer, ASUS, Dell, Gigabyte, HP and MSI
What NVIDIA means by “128GB”
NVIDIA says two DGX Spark 64GB systems linked through a 200 GbE fabric can pool their memory to 128GB when managed by NVIDIA Sync Cluster Assistant. Each announced unit contributes 64GB; the 128GB figure is the combined capacity of the pair.
The arrangement does not turn two devices into one physical machine, and the announcement does not promise that every application will see one flat, directly addressable 128GB memory region. NVIDIA describes Sync Cluster Assistant as detecting connected systems, validating their configuration, setting up the ConnectX-7 network and routing workloads across the cluster. Those are vendor capability claims rather than independent performance testing.
#1 Best Overall
How the two-system connection works
Network and software
The two systems use their ConnectX-7 networking over a 200 GbE link. Sync Cluster Assistant handles configuration and workload routing according to NVIDIA’s announcement. The assistant’s supported workflow is therefore part of the setup; simply plugging two systems together is not, by itself, a guarantee of pooled-memory behavior.
Cable type and speed
NVIDIA’s DGX Spark clustering guide specifies QSFP cables for connecting systems. Each port provides up to 200 Gb/s, but the negotiated incoming speed depends on the cable. NVIDIA recommends a cable rated for at least 200 Gb/s, notes that a cable rated above 200 Gb/s cannot raise the port’s 200 Gb/s ceiling, and lists approved Amphenol and Luxshare models.
Before buying, match the exact approved model, connector ends, length and speed rating in NVIDIA’s guide, and verify seller authenticity and compatibility for the systems you are ordering.
Do these 3 things before closing this tab:
1Repair Windows errors before they cause bigger problems2Fix the driver behind crashes, sound loss and screen glitches3Clear out junk files and repair common Windows errorsRank #2
- 140MM FAN MOUNT: Built around a 140 mm fan layout with approximately 124.5 mm hole spacing, creating a defined top-mount position for a compact workstation cooling setup
- SINGLE-PIECE DUCT: One-piece fan shroud forms a simple airflow channel between the upper vent area and a 140 mm fan position, keeping the desktop workstation setup compact
- TOP-MOUNT LAYOUT: Designed to sit above a compatible compact AI workstation, the cooling duct uses the upper device area without requiring a larger external frame
- OPEN AIRFLOW PATH: The central round passage links the workstation vent area with the fan mount, giving the setup a clear physical airflow route without internal moving parts
- COMPACT SIZE: Approx. 157 x 178 x 51 mm body keeps the fan duct close to the workstation, fitting home lab, AI development desk, and compact compute setups
Supported topologies
The guide says Sync Cluster Assistant supports up to three systems connected directly by cables and up to four systems connected through a switch. That is a broader topology limit than the announcement’s specific two-unit, 128GB claim; it should not be read as a promise that every larger arrangement provides a corresponding linear memory pool.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.What is—and is not—confirmed about the 64GB hardware
NVIDIA’s detailed hardware overview describes a DGX Spark with 128GB unified memory, a ConnectX-7 NIC, two QSFP network connectors and 1TB or 4TB NVMe M.2 storage. The retrieved guide documents that described system, while the October announcement confirms the new 64GB memory configuration but does not say that every specification carries over unchanged. Do not apply the entire 128GB model’s specification table to a 64GB SKU without checking its exact product listing.
Who the 64GB model is for
NVIDIA positions DGX Spark for desktop AI development, including prototyping, fine-tuning, inference and data science. The company’s DGX Spark product page contains detailed workload and specification claims for the 128GB configuration; those details are not independent 64GB test results.
Quick Recap
What to verify before ordering two
- Confirm that the seller’s system is the announced 64GB configuration and check the exact storage, ports and warranty terms for that SKU.
- Budget for two systems plus two compatible QSFP cables, or the required switch and cabling for a switched topology.
- Check NVIDIA’s approved cable list and ensure each cable supports at least 200 Gb/s.
- Plan to use Sync Cluster Assistant and confirm that your software workload supports its routed, multi-system workflow.
- Compare total two-node cost, support coverage and availability rather than treating $4,999 as a confirmed street price for every partner model.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
