Sari la conținut

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchProduse AI

analiza aiqbench

NVIDIA's DGX Spark 64GB offers a cost-effective entry point for running local open models and multi-agent workloads on dedicated hardware, eliminating per-token API costs as token consumption scales. By leveraging unified memory across its GB10 Grace Blackwell superchip, the system enables efficient fine-tuning and inference without data copying overheads between CPU and GPU. This configuration allows developers to cluster units for increased capacity while maintaining privacy and control over sensitive agent operations.
Sursă care acoperăMarkTechPost
Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

NVIDIA Announces DGX Spark 64GB: A 1-PetaFLOP Grace Blackwell Desktop for Local AI Agents, Fine-Tuning, and Inference

MarkTechPost6 min de cititArticolul și perspectiva sunt în engleză.

NVIDIA announced a new 64GB configuration of DGX Spark — from Acer, ASUS, Dell, Gigabyte, HP and MSI — its GB10-powered desktop AI system. It gives developers a way to start with one system for local models and agents, then cluster two 64GB units for 128GB of memory across the cluster and more compute when […] The post NVIDIA Announces DGX Spark 64GB: A 1-PetaFLOP Grace Blackwell Desktop for Local AI Agents, Fine-Tuning, and Inference appeared first on MarkTechPost.

NVIDIA announced a new 64GB configuration of DGX Spark — from Acer, ASUS, Dell, Gigabyte, HP and MSI — its GB10-powered desktop AI system. It gives developers a way to start with one system for local models and agents, then cluster two 64GB units for 128GB of memory across the cluster and more compute when workloads grow. The direct message is: Run open models and always-on agents on your own desk, then cluster DGX Spark system as the work grows – instead of on a metered API. The timing is not accidental. Agents burn tokens continuously through tool calls, retries, long context, and multi-step plans. Token consumption has grown 14x since early 2026. On a cloud API, every…

Extras afișat conform termenilor RSS ai publicației · 118 cuvinte · textul integral și figurile sunt pe site-ul publicației

Subiecte conexe