With 16gb you can comfortably run a 12b model that's been quantized. Quantizing ... | Hacker News

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

hadlock on May 2, 2025 | parent | context | favorite | on: Running Qwen3 on your macbook, using MLX, to vibe ...

With 16gb you can comfortably run a 12b model that's been quantized. Quantizing is (bad example) effectively lossy compression.

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