aiqbench analysis
The NVIDIA DGX Spark's new 64GB unified memory configuration enables the local execution of up to 100-billion-parameter models, reducing reliance on cloud infrastructure for sensitive or latency-critical AI workloads. By integrating Grace Blackwell compute with pre-configured software stacks and clustering capabilities, this hardware update directly addresses the growing demand for private, on-device inference in enterprise and research environments.
NVIDIA DGX Spark gets 64GB memory option for local AI work
NVIDIA DGX Spark will be available with 64GB of unified memory from Acer, ASUS, Dell, Gigabyte, HP and MSI, giving developers a new configuration with DGX OS and the NVIDIA AI software stack. The new SKU runs capable local agents on device, privately, without cloud dependency, and will be available starting Friday, Oct. 23.
NVIDIA will offer the DGX Spark with 64GB of unified memory starting October 23rd through partners including Acer, ASUS, Dell, Gigabyte, HP and MSI. This new configuration allows developers to run up to 100-billion-parameter models fully on device, bypassing cloud reliance for local AI work. NVIDIA states that DGX Spark combines Grace Blackwell compute, unified memory and…
Excerpt shown under the publisher's RSS terms · 57 words · full text and figures are on the publisher's site
Related coverage
A week with RTX Spark: everything we’ve learned using Nvidia’s new laptops
The Verge · Oct 16, 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026
[AINews] DeepSeek v4.1-Flash: 763B-P8B-D16B novel causal Encoder–Decoder architecture with vision marks the Return of the Whale
Latent Space · Sep 12, 2026
[AINews] High Taste Testers Ep. 1
Latent Space · Oct 17, 2026