can it run
Yes, but close to the edge. 11GB against a 10GB working set: it runs, with little room for long context windows or other processes.
weights 8GB + KV cache 3.12GB at 4k context vs ~11GB usable → tight. 11.1 of 11 GB usable — barely over; real with q8 KV cache (halves KV) or shorter context
computed roofline: 484 GB/s × 0.28–0.50 efficiency window / 8.0GB (Q4_K_M) — bands, never points.
| model file | 8.0GB (GGUF Q4_K_M) |
| minimum memory | 10GB working set |
| this machine | 11GB GDDR5X, 484 GB/s |
| params | 13B |
| license | apache-2.0 |
| price | $275 |
easy run: ollama pull llava:13b
runs with: ollama · llama.cpp · koboldcpp · lm studio
→ Tesla P100 (16GB, used) — cheapest machine that runs it ($135)
→ every model the GTX 1080 Ti (11GB, used) can run — full list
→ RTX 3090 (24GB, used) — upgrade path machine