can it run
No. 8GB of memory can't hold the 12GB working set this model needs. A smaller quant or a bigger machine is required.
| model file | 9.1GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 8GB GDDR6, 448 GB/s |
| params | 14B |
| license | mit |
| price | $250 |
easy run: ollama pull phi4:14b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla M40 (24GB, used) — cheapest machine that runs it ($50)
→ every model the RTX 3070 (used) can run — full list