NVIDIA Launches 64GB DGX Spark for Local AI Development

In short: NVIDIA is releasing a new 64GB unified memory configuration of its DGX Spark personal AI supercomputer, available from partners like Acer, ASUS, Dell, HP, Gigabyte and MSI starting Oct. 23 at $4,999. The system runs up to 100-billion-parameter models locally on device, and two units can be clustered via NVIDIA Sync Cluster Assistant to pool memory to 128GB and support models up to 200 billion parameters, with up to 1.7x performance gains in NVIDIA's Qwen 3.8 27B test. It ships with the NVIDIA Agent Toolkit, CUDA-X AI libraries, Nemotron models and support for Ollama, vLLM and PyTorch out of the box.

Source: NVIDIA2 Oct 2026, 16:00NVIDIA Original article ↗

This summary was generated automatically by AI from NVIDIA's publication. It is our own text, not a copy of the original — facts, figures and quotes belong to the source, linked above and below.

What changed?

1New 64GB DGX Spark SKU priced at $4,999, available Oct. 23 from manufacturer partners
2Supports up to 100-billion-parameter models on a single unit
3Two clustered 64GB units pool memory to 128GB, supporting up to 200-billion-parameter models with up to 1.7x performance
4Ships with NVIDIA Agent Toolkit, Nemotron models, and support for Ollama, vLLM, PyTorch
5NVIDIA Sync Model Launcher coming end of month for one-click local model deployment

Why it matters

This lowers the entry cost for running large open-weight models locally for agentic workloads, which matters for developers wanting privacy and no cloud dependency, but it's a hardware/infrastructure product rather than a direct voice-AI or API capability change.

What it means for AI agents and contact centers

Not directly relevant to your company's voice agent stack since this is a local hardware platform for running LLMs on-device rather than a voice, STT/TTS or telephony API change; could be relevant only if your company later considers on-prem/local LLM inference for privacy-sensitive deployments.

Local AI Edge Inference Hardware Agents Pricing Clustering

Sources

NVIDIAOfficialPrimary source
„NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI“
2 Oct 2026, 16:00
Licence: robots.txt Content-Signal: ai-input=yes · our summary (content changed)
Original article →

Published by source: 2 Oct 2026, 16:00
Found by our system: 2 Oct 2026, 19:51
Summary generated: 2 Oct 2026, 19:55

This article was written by AI from the original source. Facts, numbers and prices come from the source; missing values are marked “Not specified”. Legal notice, copyright and privacy