▲ local intelligence

can it run

Can the Radeon Vega 8 (iGPU) run DEEPSEEK-R1 distill 7B?

FULL

4.9 GB needed of 13.5 GB usable — headroom for context

~13.5GB usable · GCN5.1 (iGPU) · model file 4.7GB · distill 7B

~2.7–8.7 tok/s

computed roofline: 51.2 GB/s × 0.25–0.80 efficiency window / 4.7GB (Q4_K_M) — bands, never points.

Run DEEPSEEK-R1 distill 7B on instead

→ Raspberry Pi 5 + AI Kit (Hailo-8L) — cheapest catalog machine that runs DEEPSEEK-R1 distill 7B fully ($110)

→ every model the Radeon Vega 8 (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 Vega 8 (iGPU) · fit = weights + 4k KV vs usable memory