local intelligence

can it run

Can the NVIDIA B200 192GB run devstral 24B?

FULL

15.2 GB needed of 192 GB usable — headroom for context

192GB · Blackwell · model file 14.6GB · 24B

~250–420 tok/s

computed roofline: 8000 GB/s × 0.46–0.76 efficiency window / 14.6GB (Q4_K_M) — bands, never points.

Run devstral 24B on instead

Tesla M40 (24GB, used) — cheapest catalog machine that runs devstral 24B fully ($50)

NVIDIA DGX Station (GB300) — upgrade path machine

every model the NVIDIA B200 192GB can run — full list

explore the full catalog90 machines indexed · live prices · what each one can run
2026-09-24 · ← all models on the NVIDIA B200 192GB · fit = weights + 4k KV vs usable memory