Apple silicon
Nvidia confirms RTX Spark laptops for October 16, and its compact desktops move to November
Nvidia confirmed on October 13 that the first RTX Spark laptops arrive on October 16, while the compact desktops it promised for October are now due in November. We have not tested any RTX Spark machine.
- News
Ollama MLX runner becomes the default on Apple silicon, and Ollama pauses its background model upgrades
Ollama's 0.40 releases, up to 0.40.4 on 12 October 2026, run supported models on MLX by default on Apple silicon. Version 0.40.2 began upgrading older downloads in the background with backups kept, and 0.40.3 paused that upgrade.
- Research
Two models at once on a 48 GB Mac: an idle second model cut the first from 49.4 tokens a second to 14.5
Two models of about 20 GB each both load on a 48 GB Mac. With the second one idle, the working model wrote 14.5 tokens a second against 49.4 alone, and swap reached 26.7 GB.
- Research
What is MLX in LM Studio? On an M4 Pro it cut one model’s long read from 74.8 seconds to 30.3
MLX is Apple's machine learning framework, and LM Studio runs it as a second engine. On an M4 Pro it read a long prompt 2.5 times faster for Qwen 3.6 35B-A3B and 9 percent faster for Gemma 4 31B.