local intelligence

can it run

Can the Radeon 890M (iGPU) run qwen2.5vl 7B?

FULL

5.8 GB needed of 29.5 GB usable — headroom for context

~29.5GB usable · RDNA3.5 (iGPU) · model file 5.6GB · 7B

~6.1–20 tok/s

computed roofline: 136.5 GB/s × 0.25–0.80 efficiency window / 5.6GB (Q4_K_M) — bands, never points.

Run qwen2.5vl 7B on instead

Tesla P100 (16GB, used) — cheapest catalog machine that runs qwen2.5vl 7B fully ($135)

every model the Radeon 890M (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 890M (iGPU) · fit = weights + 4k KV vs usable memory