can it run
Yes, but close to the edge. 16GB against a 12GB working set: it runs, with little room for long context windows or other processes.
weights 9GB + KV cache 0.75GB at 4k context vs ~16GB usable → full. 9.8 GB needed of 16 GB usable — headroom for context
computed roofline: 448 GB/s × 0.46–0.76 efficiency window / 9.0GB (Q4_K_M) — bands, never points.
| model file | 9.0GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 16GB GDDR7, 448 GB/s |
| params | distill 14B |
| license | mit |
| price | $480 |
easy run: ollama pull deepseek-r1:14b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P40 (24GB, used) — cheapest machine that runs it ($290)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the RTX 5060 Ti 16GB can run — full list
→ rtx-5070-ti — the next step up from this machine's GPU
Amazon ↗ · Amazon ↗ (affiliate)