can it run
15.2 GB needed of 24 GB usable — headroom for context
24GB · Ampere GA102 · model file 14.6GB · 24B
computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 14.6GB (Q4_K_M) — bands, never points.
Community check: ~26 tok/s · 20-27B Q4 · 20 runs · inside our computed band — localmaxxing.com
→ Tesla P40 (24GB, used) — cheapest catalog machine that runs devstral 24B fully ($290)
→ rtx-5090 — the next step up from NVIDIA RTX 3090
→ every model the NVIDIA RTX 3090 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run