local intelligence

can it run

Can the NVIDIA L40S 48GB run qwen2.5vl 7B?

FULL

5.8 GB needed of 48 GB usable — headroom for context

48GB · Ada Lovelace · model file 5.6GB · 7B

~71–120 tok/s

computed roofline: 864 GB/s × 0.46–0.76 efficiency window / 5.6GB (Q4_K_M) — bands, never points.

Run qwen2.5vl 7B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs qwen2.5vl 7B fully ($35)

rtx-pro-6000 — the next step up from NVIDIA L40S 48GB

every model the NVIDIA L40S 48GB 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 L40S 48GB · fit = weights + 4k KV vs usable memory