can it run
Comfortably. 12GB of memory against a 7GB working set leaves headroom for context, the OS, and anything else you're running.
weights 5.2GB + KV cache 0.56GB at 4k context vs ~6GB usable → tight. 5.8 of 6 GB usable — keep context modest
computed roofline: 336 GB/s × 0.48–0.72 efficiency window / 5.2GB (Q4_K_M) — bands, never points.
| model file | 5.2GB (GGUF Q4_K_M) |
| minimum memory | 7GB working set |
| this machine | 12GB GDDR6, 336 GB/s |
| params | 8B |
| license | apache-2.0 |
| price | $375 |
easy run: ollama pull qwen3:8b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ every model the RTX 2060 12GB (used) can run — full list
→ rtx-5060-ti-16 — the next step up from this machine's GPU