(C) Alec Muffett's DropSafe blog.
Author Name: Alec Muffett
This story was originally published on allecmuffett.com. [1]
License: CC-BY-SA 3.0.[2]
 

Share on WhatsApp

2026-03 

I have a 2018-era MacMini with 64Gb of RAM + negligible GPU, running a 35 billion parameter model and I’m getting 4 tokens per second out of it; tell me again how we aren’t going to be running AIs locally at home? https://alecmuffett.com/article/148512
[END]

[1] URL: https://www.addtoany.com/add_to/whatsapp?linkurl=https%3A%2F%2Falecmuffett.com%2Farticle%2F148512&linkname=I%20have%20a%202018-era%20MacMini%20with%2064Gb%20of%20RAM%20%2B%20negligible%20GPU%2C%20running%20a%2035%20billion%20parameter%20model%20and%20I%E2%80%99m%20getting%204%20tokens%20per%20second%20out%20of%20it%3B%20tell%20me%20again%20how%20we%20aren%E2%80%99t%20going%20to%20be%20running%20AIs%20locally%20at%20home%3F
[2] URL: https://creativecommons.org/licenses/by-sa/3.0/

DropSafe Blog via Magical.Fish Gopher News Feeds:
gopher://magical.fish/1/feeds/news/alecmuffett/