local intelligence

can it run

Can the NVIDIA GTX 1070 run phi4 14B?

OFFLOAD PARTIAL

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

8GB · Pascal · model file 9.1GB · 14B

~7.9–14 tok/s

computed roofline: 256 GB/s × 0.28–0.50 efficiency window / 9.1GB (Q4_K_M) — bands, never points.

Run phi4 14B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs phi4 14B fully ($135)

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 catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA GTX 1070 · fit = weights + 4k KV vs usable memory