local intelligence

can it run

Can the Intel Arc A380 run qwen3 4B?

FULL

3.2 GB needed of 6 GB usable — headroom for context

6GB · Alchemist · model file 2.6GB · 4B

~15–37 tok/s

computed roofline: 192 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)

arc-b580 — the next step up from Intel Arc A380

every model the Intel Arc A380 can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Intel Arc A380 · fit = weights + 4k KV vs usable memory