local intelligence

can it run

Can the Radeon 740M run llava 7B?

FULL

6.7 GB needed of 13.5 GB usable — headroom for context

~13.5GB usable · RDNA3 (iGPU) · model file 4.7GB · 7B

~6.4–20 tok/s

computed roofline: 120 GB/s × 0.25–0.80 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 Radeon 740M can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Radeon 740M · fit = weights + 4k KV vs usable memory