Hacker News new | ask | show | jobs
by faangguyindia 85 days ago
U are better off just buying their coding plan.

Running LLM makes no sense whatsoever
1 comments
oompydoompy74 85 days ago
Remaining dependent on proprietary frontier models that you can only access via an API makes no sense whatsoever. My hope is that the future is open weight models running on local hardware.
link
naasking 85 days ago
Eventually, yes. ParoQuant is hopefully the future here, 4-bit weights with no real degradation from FP16:

https://github.com/z-lab/paroquant

link