local intelligence

can it run

Can the RTX 3080 Laptop run qwen3.8 27B?

OFFLOAD PARTIAL

18.5 GB vs 16 GB usable — partial CPU offload, expect large speed loss

16GB · Ampere GA104 · model file 16.5GB · 27B

~12–21 tok/s

computed roofline: 448 GB/s × 0.46–0.76 efficiency window / 16.5GB (Q4_K_M) — bands, never points.

Run qwen3.8 27B on instead

Mac mini M4 (32GB) — cheapest catalog machine that runs qwen3.8 27B fully ($999)

every model the RTX 3080 Laptop can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the RTX 3080 Laptop · fit = weights + 4k KV vs usable memory