can it run
| model file | 8.1GB (GGUF Q4_K_M) |
| minimum memory | 11GB working set |
| this machine | 2TB PCIe Gen5, ~14,500 MB/s |
| params | 12B |
| license | gemma |
| price | $304 |
easy run: ollama pull gemma3:12b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P100 (16GB, used) — cheapest machine that runs it ($135)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine