local intelligence

can it run

Can the Apple M3 Pro run qwen2.5vl 7B?

FULL

5.8 GB needed of 16 GB usable — headroom for context

~16GB usable · Apple M3 Pro · model file 5.6GB · 7B

~15–21 tok/s

computed roofline: 150 GB/s × 0.55–0.80 efficiency window / 5.6GB (Q4_K_M) — bands, never points.

Run qwen2.5vl 7B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs qwen2.5vl 7B fully ($135)

every model the Apple M3 Pro can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Apple M3 Pro · fit = weights + 4k KV vs usable memory