local intelligence

can it run

Can the AMD Radeon RX 6800 XT run qwen3 4B?

FULL

3.2 GB needed of 16 GB usable — headroom for context

16GB · RDNA2 · model file 2.6GB · 4B

~89–140 tok/s

computed roofline: 512 GB/s × 0.45–0.72 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)

rx-6900-xt — the next step up from AMD Radeon RX 6800 XT

every model the AMD Radeon RX 6800 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 6800 XT · fit = weights + 4k KV vs usable memory