local intelligence

can it run

Can the NVIDIA GeForce RTX 4070 Ti Super run qwen3.8 27B?

OFFLOAD PARTIAL

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

16GB · Ada · model file 16.5GB · 27B

~22–33 tok/s

computed roofline: 672 GB/s × 0.54–0.80 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)

rtx-4090 — the next step up from NVIDIA GeForce RTX 4070 Ti Super

every model the NVIDIA GeForce RTX 4070 Ti Super 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 GeForce RTX 4070 Ti Super · fit = weights + 4k KV vs usable memory