local intelligence

can it run

Can the NVIDIA RTX 3090 run qwen3.8 27B?

FULL

18.5 GB needed of 24 GB usable — headroom for context

24GB · Ampere GA102 · model file 16.5GB · 27B

~26–43 tok/s

computed roofline: 936 GB/s × 0.46–0.76 efficiency window / 16.5GB (Q4_K_M) — bands, never points.

Community check: ~26 tok/s · 20-27B Q4 · 20 runs · inside our computed band — localmaxxing.com

Run qwen3.8 27B on instead

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

rtx-5090 — the next step up from NVIDIA RTX 3090

every model the NVIDIA RTX 3090 can run — full list

explore the full catalog84 machines indexed · live prices · what each one can run
2026-09-17 · ← all models on the NVIDIA RTX 3090 · fit = weights + 4k KV vs usable memory