local intelligence

can it run

Can the NVIDIA Titan Xp 12GB run PHI4 mini 3.8B?

FULL

3.0 GB needed of 12 GB usable — headroom for context

12GB · Pascal · model file 2.5GB · mini 3.8B

~61–110 tok/s

computed roofline: 547.6 GB/s × 0.28–0.50 efficiency window / 2.5GB (Q4_K_M) — bands, never points. Small models (under ~4.5B) run BELOW these bands — kernel-launch overhead keeps them from saturating bandwidth (measured against community medians, 09-06).

Run PHI4 mini 3.8B on instead

Tesla M60 (16GB, used) — cheapest catalog machine that runs PHI4 mini 3.8B fully ($35)

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

every model the NVIDIA Titan Xp 12GB 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 Titan Xp 12GB · fit = weights + 4k KV vs usable memory