can it run
Comfortably. 12GB of memory against a 4GB working set leaves headroom for context, the OS, and anything else you're running.
weights 3.1GB + KV cache 2GB at 4k context vs ~6GB usable → tight. 5.1 of 6 GB usable — keep context modest
computed roofline: 336 GB/s × 0.48–0.72 efficiency window / 3.1GB (Q4_K_M) — bands, never points.
| model file | 3.1GB (GGUF Q4_K_M) |
| minimum memory | 4GB working set |
| this machine | 12GB GDDR6, 336 GB/s |
| params | medium |
| license | apache-2.0 |
| price | $375 |
easy run: no stock runtime yet
→ every model the RTX 2060 12GB (used) can run — full list
→ rtx-5060-ti-16 — the next step up from this machine's GPU