# Nvidia's RTX Spark laptops go on sale with up to 128GB of unified memory as new papers cut the memory cost of small and mixture-of-experts models

A 46 MB ternary model with a frozen 16 MB vocabulary generates 615 to 740 tokens per second on a laptop CPU, and a second paper finds that about 4% of prompt tokens need full expert routing to preserve accuracy.

- Published: 2026-10-19T06:14:35.233Z
- Canonical: https://polylog.news/ai/2026-10-19/nvidia-s-rtx-spark-laptops-go-on-sale-with-up-to-128gb-of-un
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [NVIDIA Blog](https://blogs.nvidia.com/blog/local-ai-rtx-spark-windows-laptops-celebration/), [arXiv cs.CL](https://arxiv.org/abs/2610.22428), [arXiv cs.CL](https://arxiv.org/abs/2610.22454), [PC Gamer](https://pcgamer.com/hardware/gaming-laptops/now-we-know-the-prices-of-the-new-rtx-spark-laptops-and-theyre-as-expensive-as-im-sure-you-feared), [IBTimes UK](https://www.ibtimes.co.uk/rtx-spark-laptop-prices-local-ai-1824551)

Nvidia said RTX Spark laptops are now available from ASUS, Dell, HP, Lenovo, Microsoft and MSI. They combine Blackwell RTX graphics with up to 128GB of unified memory and Nvidia's full AI software stack, and Nvidia quotes a starting price o…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-19/nvidia-s-rtx-spark-laptops-go-on-sale-with-up-to-128gb-of-un (subscription information: https://polylog.news/pricing).