If "small models" is the bar, then you can run inference for ~$50 on Raspberry P... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

bigyabai 89 days ago | parent | context | favorite | on: MacBook M5 Pro and Qwen3.5 = Local AI Security Sys...

If "small models" is the bar, then you can run inference for ~$50 on Raspberry Pi like hardware. I do that with 1.8b-4b models.

aegis_camera 89 days ago [–]

LFM 450M for vision task, QWEN 9B Q4 for Orchestration, this provides a good result.

hparadiz 89 days ago | [–]

I actually meant a context window of about 50k which is what you need to run OpenClaw well.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact