▲ local intelligence

can it run

Can the NVIDIA RTX 2070 run llava 7B?

TIGHT

6.7 of 8 GB usable — keep context modest

8GB · Turing TU106 · model file 4.7GB · 7B

~46–69 tok/s

computed roofline: 448 GB/s × 0.48–0.72 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run llava 7B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs llava 7B fully ($35)

→ 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