local intelligence

can it run

Can the AMD Radeon RX 590 / 590 GME 8GB run qwen2.5vl 7B?

FULL

5.8 GB needed of 8 GB usable — headroom for context

8GB · Polaris (GCN 4) · model file 5.6GB · 7B

~3.7–9.6 tok/s

computed roofline: 256 GB/s × 0.08–0.21 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)

rtx-3060-12 — the next step up from AMD Radeon RX 590 / 590 GME 8GB

every model the AMD Radeon RX 590 / 590 GME 8GB 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 590 / 590 GME 8GB · fit = weights + 4k KV vs usable memory