local intelligence

can it run

Can the AMD RX 6700 XT run qwen3 4B?

FULL

3.2 GB needed of 12 GB usable — headroom for context

12GB · RDNA2 gfx1031 · model file 2.6GB · 4B

~30–74 tok/s

computed roofline: 384 GB/s × 0.20–0.50 efficiency window / 2.6GB (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 qwen3 4B on instead

Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs qwen3 4B fully ($110)

radeon-9070-xt — the next step up from AMD RX 6700 XT

every model the AMD RX 6700 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 RX 6700 XT · fit = weights + 4k KV vs usable memory