can it run
| model file | 3.3GB (GGUF Q4_K_M) |
| minimum memory | 5GB working set |
| this machine | external GPU dock, built-in PSU |
| params | 4B |
| license | gemma |
| price | $229 |
easy run: ollama pull gemma3:4b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest machine that runs it ($110)