▲ local intelligence

can it run

Can the NVIDIA RTX 2070 run devstral 24B?

NO

15.2 GB vs 8 GB usable — does not fit

8GB · Turing TU106 · model file 14.6GB · 24B

~15–22 tok/s

computed roofline: 448 GB/s × 0.48–0.72 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)

→ RTX 3090 (24GB, used) — upgrade path machine

→ every model the NVIDIA RTX 2070 can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the NVIDIA RTX 2070 · fit = weights + 4k KV vs usable memory