can it run
11.1 of 13.5 GB usable — keep context modest
~13.5GB usable · Adreno (iGPU) · model file 8.0GB · 13B
computed roofline: 135.2 GB/s × 0.25–0.80 efficiency window / 8.0GB (Q4_K_M) — bands, never points.
→ Tesla P100 (16GB, used) — cheapest catalog machine that runs llava 13B fully ($135)
→ every model the Adreno X1-45 (Snapdragon X Plus) can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run