local intelligence

can it run

Can the AMD Radeon RX 7900 XTX run gemma3 4B?

FULL

3.8 GB needed of 24 GB usable — headroom for context

24GB · RDNA3 · model file 3.3GB · 4B

~150–220 tok/s

computed roofline: 960 GB/s × 0.50–0.75 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-3090 — the next step up from AMD Radeon RX 7900 XTX

every model the AMD Radeon RX 7900 XTX can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the AMD Radeon RX 7900 XTX · fit = weights + 4k KV vs usable memory