alt Hacker News> SSD streaming to GPU
Is this solution based on what Apple describes in their 2023 paper 'LLM in a flash' [1]?
Replies
zozbot234 • today at 3:33 PM
A similar approach was recently featured here: https://news.ycombinator.com/item?id=47476422 Though iPhone Pro has very limited RAM (12GB total) which you still need for the active part of the model. (Unless you want to use Intel Optane wearout-resistant storage, but that was power hungry and thus unsuitable to a mobile device.)
➕ show 2 replies
foobiekr • today at 4:11 PM
This is not entirely dissimilar to what Cerebus does with their weights streaming.
➕ show 1 reply
Yes. I collected some details here: https://simonwillison.net/2026/Mar/18/llm-in-a-flash/