Yhn ScienceBiology first seen 2 d ago, last 1 h ago, peak #4
Developers compare hardware for running local AI models
Original: Ask HN: What hardware are you using to run local LLMs?
A Hacker News discussion asks what hardware people are using to run large language models locally. Respondents are comparing consumer GPUs, Macs with unified memory, and other setups as interest grows in running AI models on personal machines instead of cloud services, trading off cost, memory capacity, and inference speed.
Why now: Growing interest in privacy, cost savings, and independence from cloud AI providers is driving hobbyists and developers to experiment with running language models on their own machines.
Hacker Newslocal LLMsconsumer GPUsApple Mac
Evidence
- Ask HN: What hardware are you using to run local LLMs? · leafletsigh · 52
API: https://socialmediatrends-api.osmike.com/v1/trends/4637305