Thread

1. wasting_time · 1790884160 · focus · HN ↗

   So, how are people actually using Pi? Here I am with Claude Code and Codex in a terminal like a caveman.

   1. whiteblossom · 1790884725 · focus · HN ↗

      It's been pretty useful for experimenting with local models due to its more light-weight approach. Though I respect the creators a ton, OpenCode has not seemed to work as well with models that run on consumer hardware

      1. unsnap_biceps · 1790885736 · focus · HN ↗

         Which models are you finding the most success with?

         1. hypercube33 · 1790890980 · focus · HN ↗

            I have more beefcake machines and Qwen 4.6 36B has been awesome for coding. Its fast for a local model, seems to get a lot right most of the time, just its slower than OpenAI/Claude/Cloud Hosted stuff since I dont have a 24GB+ GPU (I have Strix Halo and a 12GB GPU)

            1. vhantz · 1790919985 · focus · HN ↗

               How many token/s do you get with that setup?

               1. hypercube33 · 1791147530 · focus · HN ↗

                  60-70 tokens/sec Windows 11 LLM Studio 250 or whatever the models max is below that as context Qwen3.6 35B A3B 35B-A3B, gguf

Unofficial Hacker News client; not affiliated with Y Combinator.