can it run
15.2 GB vs 12 GB usable — does not fit
12GB · Volta · model file 14.6GB · 24B
computed roofline: 652.8 GB/s × 0.46–0.76 efficiency window / 14.6GB (Q4_K_M) — bands, never points.
→ Tesla M40 (24GB, used) — cheapest catalog machine that runs devstral 24B fully ($50)
→ tesla-v100-32gb — the next step up from NVIDIA Titan V 12GB
→ every model the NVIDIA Titan V 12GB can run — full list
→explore the full catalog90 machines indexed · live prices · what each one can run