▲ local intelligence

can it run

Can the NVIDIA GeForce RTX 4080 SUPER run gemma3 1B?

FULL

1.1 GB needed of 16 GB usable — headroom for context

16GB · Ada · model file 1.0GB · 1B

~370–590 tok/s

computed roofline: 736 GB/s × 0.50–0.80 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)

→ rtx-4090 — the next step up from NVIDIA GeForce RTX 4080 SUPER

→ every model the NVIDIA GeForce RTX 4080 SUPER 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 GeForce RTX 4080 SUPER · fit = weights + 4k KV vs usable memory