can it run
Only with compromises. 10GB is below the 12GB working set — expect a lower quant, offloading, or heavy swap. Possible, not pleasant.
| model file | 9.3GB (GGUF Q4_K_M) |
| minimum memory | 12GB working set |
| this machine | 10GB GDDR6X, 760 GB/s |
| params | 14B |
| license | apache-2.0 |
| price | $350 |
easy run: ollama pull qwen3:14b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla M40 (24GB, used) — cheapest machine that runs it ($50)
→ ASUS ExpertCenter Pro ET900N G3 (GB300) — this model on the biggest machine
→ every model the RTX 3080 10GB (used) can run — full list