local intelligence

can it run

Can the NVIDIA GeForce GTX 1660 Ti 6GB run gemma3 4B?

FULL

3.8 GB needed of 6 GB usable — headroom for context

6GB · Turing · model file 3.3GB · 4B

~42–63 tok/s

computed roofline: 288 GB/s × 0.48–0.72 efficiency window / 3.3GB (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 gemma3 4B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs gemma3 4B fully ($110)

rtx-3060-ti — the next step up from NVIDIA GeForce GTX 1660 Ti 6GB

every model the NVIDIA GeForce GTX 1660 Ti 6GB 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 GeForce GTX 1660 Ti 6GB · fit = weights + 4k KV vs usable memory