Free tools Windows power users keep installed
One-click scans. No signup required.
NVIDIA has announced a 64GB unified-memory version of DGX Spark, with a starting price of $4,999 and availability through manufacturer partners scheduled for October 23, 2026. NVIDIA says the smaller-memory configuration retains the GB10 Grace Blackwell Superchip, DGX OS and its AI software stack, and can run local models with up to 100 billion parameters. Those are vendor claims; the announced price is a starting price, not a confirmed transaction price.
What is changing with DGX Spark?
The new configuration halves the memory capacity of the 128GB DGX Spark, while NVIDIA says it keeps the same GB10 Grace Blackwell platform and software stack. The company announced the 64GB model on October 2, 2026, and named Acer, ASUS, Dell, Gigabyte, HP and MSI as manufacturer partners. NVIDIA scheduled availability to begin October 23, 2026, so that date was still in the future when announced.
NVIDIA calls the memory unified, meaning the 64GB is the system’s shared memory pool rather than a separate 64GB graphics-memory allowance. The announcement positions the computer for local AI agents, model inference, fine-tuning, data science and edge development.
Price and availability
NVIDIA announced a starting price of $4,999 for the 64GB configuration. It is a relative lower-memory option within the DGX Spark line, but the announcement does not establish the current price of the 128GB model or the eventual price charged by each partner. The 64GB version is being offered through the named manufacturer partners; NVIDIA’s announcement does not confirm a particular retailer listing or current inventory. See NVIDIA’s October 2 announcement for its price and timing claims.
Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWindows Errors? Fix Them Before They Spread
Repair common Windows errors and clear accumulated junk for a smoother, more stable PC - no reinstall needed.Free scan · no reinstall#1 Best Overall
- Supercomputer performance directly to your desk in a compact, energy-efficient design, enabling enterprise-scale AI and high-performance computing right where you need it.
- The power of Grace Blackwell architecture, delivering up to 1 petaFLOP of AI performance for local model fine-tuning, inference, and analytics, accelerating your time-to-solution.
- Designed from the ground up to build and run AI, delivering seamless integration of the full NVIDIA AI software stack —so you can develop locally and deploy anywhere.
- NVIDIA DGX Spark gives you the freedom to experiment, prototype, and innovate faster by augmenting laptop, desktop, cloud, or data center resources. With more power to learn, prototype, test, and innovate, NVIDIA DGX Spark delivers exceptional ROI for increased productivity.
- Use NVIDIA DGX Spark to unlock new ideas and experiment with large models (up to 200 billion parameters at FP4) directly on your desktop with 128GB of unified memory. Empower rapid testing, validation, and iteration—driving innovation in a secure, high-performance setting.
What NVIDIA says the 64GB system can run
NVIDIA says one 64GB DGX Spark supports local models up to 100 billion parameters. Parameter count is only a rough indication of model scale: it does not by itself tell you how quickly a model will run, which precision or context length will fit, or what quality to expect. The announcement does not publish those details for specific models or workloads.
For a buyer, the practical question is whether the intended model and workload fit the available memory and software configuration—not simply whether the parameter count is below NVIDIA’s stated ceiling. Treat the 100-billion figure as NVIDIA’s capability claim, not a guarantee of a particular speed or user experience.
Rank #2
Can two 64GB systems work together?
NVIDIA says two 64GB units can be connected over their 200 GbE fabric using NVIDIA Sync Cluster Assistant, pooling memory to 128GB and supporting models up to 200 billion parameters. The company describes connecting the machines directly with a QSFP cable; Sync detects the connected units and configures the ConnectX-7 network. This approach means acquiring a second system, not upgrading one unit’s memory.
NVIDIA also reports up to 1.7x performance versus a single system in its test of Qwen 3.8 27B on two clustered units. That is a manufacturer-reported result for the named model and setup; it does not establish the same gain for other models, workloads or benchmarks. NVIDIA’s blog quotes author Allen Bourgoyne: “Two 64GB units clustered together don’t just double the memory.”
Rank #3
- 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
Check the exact specifications before buying
NVIDIA’s product page and hardware guide describe the 128GB DGX Spark configuration with 4TB NVMe storage, 273GB/s memory bandwidth, ConnectX-7 networking, Wi-Fi 7 and up to 1 PFLOP FP4 performance. Those figures are explicitly associated with the 128GB system and should not be assumed to apply to the newly announced 64GB model. Check a partner’s listing or an updated official specification page for the exact SKU before relying on storage, networking or performance details.
For context, consult the DGX Spark product page and the DGX Spark hardware guide; both provide platform information, but their cited detailed specifications are for the 128GB configuration. NVIDIA’s earlier DGX Spark launch announcement also cautions that product features, specifications, availability and pricing may change.
Who should consider the 64GB DGX Spark?
The configuration may be relevant if you want NVIDIA’s local-AI software and hardware platform but do not need the 128GB model’s capacity. Before deciding, compare the exact workloads you plan to run, memory needs, measured performance on those workloads, software and framework support, upgrade or clustering path, storage and connectivity, power use, physical footprint, price and actual availability. The announcement does not provide independent tests of the 64GB system or a complete comparison with competing local-AI computers.
Quick Recap
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.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minute
