▲ local intelligence

can it run

Can the NVIDIA GTX 1070 run gemma3 12B?

OFFLOAD PARTIAL

9.6 GB vs 8 GB usable — partial CPU offload, expect large speed loss

8GB · Pascal · model file 8.1GB · 12B

~8.8–16 tok/s

computed roofline: 256 GB/s × 0.28–0.50 efficiency window / 8.1GB (Q4_K_M) — bands, never points.

Run gemma3 12B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs gemma3 12B fully ($35)

→ rtx-5060-ti-16 — the next step up from NVIDIA GTX 1070

→ every model the NVIDIA GTX 1070 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 GTX 1070 · fit = weights + 4k KV vs usable memory