Re:Mesh LLM: distributed AI computing on iroh
by josefrichter on Sunday July 12, 2026 @03:36AM
(#48879166)
Is there a catch? If not, this would be super useful.
[ Parent
| on HN ]
Re:Mesh LLM: distributed AI computing on iroh
by stymaar on Sunday July 12, 2026 @04:15AM
(#48879347)
The catch is that the token generation speed is going to be limited by network latency, making it unbearably slow to run over the internet.
It can be great on a local network though, especially if your workload is prefill-heavy (more text input to process than output tokens to emit).