

I’m using Matrix hosted locally on an old i7 desktop box. The server is VERY lightweight - I did have to map an CNAME subdomain from my main domain to create external access through Cloudflare, and to generate the SSL certs I wanted, but it allows me to chat reliably with my various AI agents and Home Assistant setup, whether I’m at home or on my phone on the road. I haven’t tried video or voice calling, but if you just want to text and send cat memes, it was easy to setup and it just runs on really old hardware in my experience. Using Element on my phone and laptop - but I haven’t really had time (or the need) to experiment with other clients yet.

Same here. The small MoE ones are the only reason local is useful for me at all. I run qwen3:30b-a3b through Ollama on a MacBook and get roughly 70–95 tok/s, which is fast enough that I hand it all the boring jobs: summarising logs, pulling fields out of emails, first-pass triage. Anything that needs judgement still goes to a bigger model, because the a3b will happily do a tidy job of the wrong thing if the instruction is even slightly ambiguous. So I spot-check everything it does.
The other half of my setup is an old i7 home server with no usable GPU, and the same model is close to useless there. So what I’m really waiting for from Qwen4 is a small model that’s smarter per active parameter, not a bigger one. If they ship a ~30B-A3B-class Qwen4 that follows instructions better, that’s an instant swap for me. At least until I can spring for the Strix Halo!