▲ local intelligence

can it run

Can the Radeon 680M run llava 7B?

FULL

6.7 GB needed of 13.5 GB usable — headroom for context

~13.5GB usable · RDNA2 (iGPU) · model file 4.7GB · 7B

~5.4–17 tok/s

computed roofline: 102.4 GB/s × 0.25–0.80 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run llava 7B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs llava 7B fully ($35)

→ every model the Radeon 680M can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the Radeon 680M · fit = weights + 4k KV vs usable memory