▲ local intelligence

can it run

Can the RTX 4070 Laptop run gemma3 1B?

FULL

1.1 GB needed of 8 GB usable — headroom for context

8GB · Ada AD106 · model file 1.0GB · 1B

~210–340 tok/s

computed roofline: 448 GB/s × 0.46–0.76 efficiency window / 1.0GB (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 1B on instead

→ Tesla M60 (16GB, used) — cheapest catalog machine that runs gemma3 1B fully ($35)

→ every model the RTX 4070 Laptop can run — full list

→explore the full catalog91 machines indexed · live prices · what each one can run
2026-10-01 · ← all models on the RTX 4070 Laptop · fit = weights + 4k KV vs usable memory