local intelligence

can it run

Can the Radeon 8060S (iGPU) run qwen3 32B?

FULL

21.0 GB needed of 29.5 GB usable — headroom for context

~30GB usable · RDNA3.5 (iGPU) · model file 20GB · 32B

~7.7–11 tok/s

computed roofline: 256 GB/s × 0.60–0.85 efficiency window / 20.0GB (Q4_K_M) — bands, never points.

Run qwen3 32B on instead

Mac mini M4 (32GB) — cheapest catalog machine that runs qwen3 32B fully ($999)

every model the Radeon 8060S (iGPU) can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the Radeon 8060S (iGPU) · fit = weights + 4k KV vs usable memory