local intelligence

can it run

Can the AMD Radeon RX 9070 (non-XT) run llama3.2 3B?

FULL

2.4 GB needed of 16 GB usable — headroom for context

16GB · RDNA4 · model file 2.0GB · 3B

~180–260 tok/s

computed roofline: 640 GB/s × 0.55–0.82 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).

Run llama3.2 3B on instead

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

radeon-9070-xt — the next step up from AMD Radeon RX 9070 (non-XT)

every model the AMD Radeon RX 9070 (non-XT) 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 9070 (non-XT) · fit = weights + 4k KV vs usable memory