local intelligence

can it run

Can the AMD Radeon RX 570 4GB run llama3.2 3B?

FULL

2.4 GB needed of 4 GB usable — headroom for context

4GB · Polaris (GCN 4) · model file 2.0GB · 3B

~9–24 tok/s

computed roofline: 224 GB/s × 0.08–0.21 efficiency window / 2.0GB (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).

Community check: ~28 tok/s · 3-4B Q4 · 3 runs · above our band — small sample; documented outlier, computed window stands — localmaxxing.com

Run llama3.2 3B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs llama3.2 3B fully ($110)

rx-580-8gb — the next step up from AMD Radeon RX 570 4GB

every model the AMD Radeon RX 570 4GB 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 570 4GB · fit = weights + 4k KV vs usable memory