can it run
| model file | 2.0GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 2-4x RTX 5090/4090 configs |
| params | 3B |
| license | llama3.2 (gated on HF) |
| price | $12000 |
easy run: ollama pull llama3.2:3b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest machine that runs it ($110)