local intelligence

can it run

Can the Radeon 680M run devstral 24B?

OFFLOAD PARTIAL

15.2 GB vs 13.5 GB usable — partial CPU offload, expect large speed loss

~13.5GB usable · RDNA2 (iGPU) · model file 14.6GB · 24B

~1.8–5.6 tok/s

computed roofline: 102.4 GB/s × 0.25–0.80 efficiency window / 14.6GB (Q4_K_M) — bands, never points.

Run devstral 24B on instead

Tesla P40 (24GB, used) — cheapest catalog machine that runs devstral 24B fully ($290)

every model the Radeon 680M 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 680M · fit = weights + 4k KV vs usable memory