Re:Ask HN: What's your current AI agentic setup?
by big-chungus4 on Thursday November 05, 2026 @01:07AM
(#50375773)
I use free models in opencode, mainly DeepSeek, but it turns out my laptop can run Qwen3.8 flash next with strata at 60 tok/s via Strata. So I mostly use Qwen now in a customized version of pi. But when I need the GPU to be free, I have to use free models in opencode. I don't use any orchestration - free models don't have high enough limits for that, and local model has only 1 conversion cache slot, more won't fit to my RAM
[ Parent
| on HN ]