can it run
15.2 GB needed of 32 GB usable — headroom for context
32GB · GCN5.1 · model file 14.6GB · 24B
computed roofline: 1024 GB/s × 0.28–0.45 efficiency window / 14.6GB (Q4_K_M) — bands, never points.
→ Tesla P40 (24GB, used) — cheapest catalog machine that runs devstral 24B fully ($290)
→ RTX 3090 (24GB, used) — upgrade path machine
→ every model the AMD Radeon Instinct MI60 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run