{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor","json":"https://digestai.news/story/nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor.json","markdown":"https://digestai.news/story/nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor.md","slug":"nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor","headline":"NVIDIA launches DGX Spark 64GB with 100-billion-parameter model support","summary":"The system features the GB10 Grace Blackwell Superchip, DGX OS, and full NVIDIA AI software stack, supporting up to 100-billion-parameter models locally. Two units can cluster via NVIDIA Sync Cluster Assistant to pool memory to 128GB and support up to 200-billion-parameter models, delivering up to 1.7x performance in Qwen 3.8 27B tests. The platform includes NVIDIA Agent Toolkit, CUDA-X AI libraries, Nemotron open models, and support for Ollama, vLLM, and PyTorch with CUDA out of the box.","keyPoints":["DGX Spark 64GB starts at $4,999 and is available from Acer, ASUS, Dell, Gigabyte, HP and MSI on October 23, 2026","Supports up to 100-billion-parameter models on a single unit and up to 200 billion when two units are clustered","Two clustered 64GB systems deliver up to 1.7x performance in NVIDIA's Qwen 3.8 27B test"],"whyItMatters":"The DGX Spark 64GB lowers the barrier for developers to run large AI models locally, enabling private agent development and reducing reliance on cloud inference for edge and personal AI workloads.","category":{"slug":"hardware","name":"Hardware & Compute","url":"https://digestai.news/category/hardware"},"entities":{"companies":["NVIDIA","Acer","ASUS","Dell","Gigabyte","HP"],"models":["Qwen 3.8 27B","Nemotron"],"people":[]},"firstPublishedAt":"2026-10-02T13:00:39Z","updatedAt":"2026-10-02T13:00:39Z","sourceCount":4,"hasPrimarySource":true,"sources":[{"outlet":"NVIDIA Blog","title":"NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI","url":"https://blogs.nvidia.com/blog/local-ai-dgx-spark-64gb-sync","publishedAt":"2026-10-02T13:00:39Z","type":"primary","primary":true,"lead":true},{"outlet":"Tom's Hardware","title":"Nvidia introduces 64GB DGX Spark to throw local AI fans a lifeline amid the RAMpocalypse","url":"https://tomshardware.com/pc-components/gpus/nvidia-introduces-64gb-dgx-spark-to-throw-local-ai-fans-a-lifeline-amid-the-rampocalypse-new-gb10-config-starts-at-usd4999-for-those-who-can-work-with-less","publishedAt":"2026-10-02T13:00:00Z","type":"press","primary":false,"lead":false},{"outlet":"wccftech.com","title":"NVIDIA’s 64 GB DGX Spark “AI Supercomputer” Launches This Month For $4999, While The 128 GB Spark Jumps Past $6000","url":"https://wccftech.com/nvidia-64-gb-dgx-spark-this-month-for-4999-usd-128-gb-spark-jumps-past-6000","publishedAt":"2026-10-02T05:59:00Z","type":"press","primary":false,"lead":false},{"outlet":"videocardz.com","title":"NVIDIA DGX Spark drops to 64GB memory but costs more than the original 128GB version","url":"https://videocardz.com/newz/nvidia-dgx-spark-drops-to-64gb-memory-but-costs-more-than-the-original-128gb-version","publishedAt":"2026-10-01T18:41:00Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"NVIDIA launches DGX Spark 64GB with 100-billion-parameter model support\", 2 October 2026, https://digestai.news/story/nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor","publisher":"Digest AI","title":"NVIDIA launches DGX Spark 64GB with 100-billion-parameter model support","datePublished":"2026-10-02T13:00:39Z","url":"https://digestai.news/story/nvidia-launches-dgx-spark-64gb-with-100-billion-parameter-model-suppor"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}