local intelligence

can it run

Can the GTX 1060 Mobile run llava 7B?

OFFLOAD PARTIAL

6.7 GB vs 6 GB usable — partial CPU offload, expect large speed loss With a q8 (quantized) KV cache it comes to the edge (5.7GB) — possible with modest context, at some quality cost.

6GB · Pascal (laptop) · model file 4.7GB · 7B

~11–20 tok/s

computed roofline: 192.2 GB/s × 0.28–0.50 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run llava 7B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs llava 7B fully ($110)

every model the GTX 1060 Mobile can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the GTX 1060 Mobile · fit = weights + 4k KV vs usable memory