/dev/null
Sign in

Commit

0d1e43c

Mike Lehan@M1ke
Anyone running coding agents for work on their own hardware? Wondering if there's a route for straightforward workflows like support ticket first response or alert triage to run on open weights from an office machine. If you're on your own gear, what did it cost you?

commit 0d1e43c

T
trijste
I had a model hosted on my home computer that I could use through a Tailscale connection, but performance was bad, and so was the output, lol. Not because of the network, but because of the hardware and the model I was able to run at the time.
MA
Md. Khorshed Alam
A refurbished Mac Studio with 64GB unified memory runs quantized 32B coding and triage models comfortably via Ollama or vLLM without sounding like a jet engine. For ticket triage and log summarization, a 14B or 32B model on local metal pays for itself pretty quickly.