DNA Insider
繁中
Back
Official Source· NVIDIA AI Blog· Published Oct 7, 2026

「Scale Local AI」 — 「Gives Developers More Ways」 — 「NVIDIA DGX Spark 64GB」 — NVIDIA Adds a 64GB DGX Spark Configuration With Two-System Clustering

NVIDIA says a 64GB unified-memory DGX Spark is planned to be available this month through Acer, ASUS, Dell, Gigabyte, HP and MSI. Two units can be clustered to pool 128GB of memory.

「Scale Local AI」 — 「Gives Developers More Ways」 — 「NVIDIA DGX Spark 64GB」 — NVIDIA Adds a 64GB DGX Spark Configuration With Two-System Clustering

Full Report

NVIDIA plans to offer DGX Spark with 64GB of unified memory this month through manufacturer partners Acer, ASUS, Dell, Gigabyte, HP and MSI. The configuration is available exclusively through those partners. NVIDIA says it includes the GB10 Grace Blackwell Superchip, DGX OS and the NVIDIA AI software stack, matching the 128GB model in those respects. NVIDIA's product page also lists a 128GB configuration.

NVIDIA says a single 64GB DGX Spark can run models with up to 100 billion parameters on-device. With NVIDIA Sync Cluster Assistant, two systems can be clustered to pool 128GB of memory and support models up to 200 billion parameters, with twice the memory bandwidth of one unit. The systems can connect directly with a QSFP cable, and the assistant helps configure their built-in ConnectX-7 networking.

In NVIDIA's Qwen 3.8 27B test, a cluster of two 64GB systems delivered up to 1.7 times the performance of one system. NVIDIA says the systems use the same software stack, so scaling from one to two does not require reconfiguration. DGX Spark is positioned for agents, inference, fine-tuning, data science and edge development; supported software includes NVIDIA Agent Toolkit, CUDA-X AI libraries, Nemotron open models, Ollama, vLLM and PyTorch with CUDA.

Why This Matters

The 64GB option broadens the memory configurations available for DGX Spark, while clustering two systems offers a way to pool 128GB for local workloads. NVIDIA's stated model-size limits and Qwen test provide concrete comparison points for developers weighing a single system against a two-system setup.

Evidence

Start with the primary evidence, then review supporting sources and context.

1 items

Primary Evidence

1
  • OfficialNVIDIA AI BlogDocumentOriginal

    NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI

    Allen Bourgoyne

    “Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally. Coming this month, NVIDIA DGX Spark will be available with 64GB of unified memory from top manufacturer partners — Acer, [...]”

Recommended signals

Recommended by brand, topic, and recent related coverage

No more recommended signals right now

Official statement

Open original source
Back to Live FeedExplore more signals