{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc","json":"https://digestai.news/story/nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc.json","markdown":"https://digestai.news/story/nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc.md","slug":"nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc","headline":"NVIDIA launches RTX Spark for personal agents and DGX Spark 64GB on Oct. 23","summary":"NVIDIA used its GTC Berlin event to unveil a full line of local AI hardware. The RTX Spark laptop, released the week before the show, is marketed for personal agents on Windows PCs and offers up to 128GB of unified memory, 1 petaflop of AI compute and 1440p gaming at 100 fps. Underdog, a desktop‑agent app that runs entirely on‑device, is now available for download on RTX Spark.\n\nThe company also announced the DGX Spark 64GB system, which ships on Friday, Oct. 23, and can be linked with up to eight units for a 1 TB unified‑memory cluster. Developers can run frontier models such as Nemotron 3.5 Bolt 74B, Qwen3.8 27B and Gemma 4 26B‑A4B on the hardware. NVIDIA Sync will add a Model Launcher later this month to simplify model deployment. DGX Station, aimed at larger teams, provides 748GB of coherent memory, up to 20 petaflops of AI performance and will arrive for Windows in December.\n\nRecursive Flint, a new 40‑billion‑parameter local coding LLM built by Recursive Superintelligence, is released with open weights under an Apache 2.0 license. It runs at over 220 tokens per second on a 64GB RTX Spark and scores highly on SWE‑Bench‑Pro v2 and related coding benchmarks. Day‑zero support was added for several other models, including Nemotron Bolt E4B 4GB and FLUX.3 Image Klein.","keyPoints":["RTX Spark launches with up to 128GB memory, 1 petaflop AI compute and supports the Underdog desktop‑agent app","DGX Spark 64GB becomes available on Oct. 23 and can cluster up to eight units for 1 TB unified memory","Recursive Flint, a 40‑billion‑parameter coding LLM, is released with open weights and runs over 220 tokens/second on RTX Spark"],"whyItMatters":"Local AI hardware lets developers run frontier models on‑premise, reducing cloud costs and data‑privacy concerns while enabling personal agents and enterprise workflows.","category":{"slug":"hardware","name":"Hardware & Compute","url":"https://digestai.news/category/hardware"},"entities":{"companies":["NVIDIA","ASUS","Dell Technologies","HP","Lenovo","Microsoft"],"models":["Nemotron 3.5 Bolt 74B","Recursive Flint","Nemotron Bolt E4B 4GB","GLM 5.3","Qwen3.8 27B","FLUX.3 Image Klein"],"people":["Jensen Huang"]},"firstPublishedAt":"2026-10-21T10:50:37Z","updatedAt":"2026-10-21T10:50:37Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"NVIDIA Blog","title":"Bringing the Spark to Europe: Local Intelligence Powers Next Wave of Agents","url":"https://blogs.nvidia.com/blog/local-ai-gtc-rtx-dgx-spark-station-sync","publishedAt":"2026-10-21T10:50:37Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Nvidia Unveils New AI Chips And Data Centers","url":"https://digestai.news/thread/nvidia-launches-rtx-spark-pc-for-creators-and-ai-agents","storyCount":4},"cite":{"text":"Digest AI, \"NVIDIA launches RTX Spark for personal agents and DGX Spark 64GB on Oct. 23\", 21 October 2026, https://digestai.news/story/nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc","publisher":"Digest AI","title":"NVIDIA launches RTX Spark for personal agents and DGX Spark 64GB on Oct. 23","datePublished":"2026-10-21T10:50:37Z","url":"https://digestai.news/story/nvidia-launches-rtx-spark-for-personal-agents-and-dgx-spark-64gb-on-oc"},"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"}