can it run
166.0 GB vs 12 GB usable — does not fit
12GB · Ampere · model file 164GB · 320B-A18B MoE
computed roofline: 912.4 GB/s × 0.46–0.76 efficiency window / 9.2GB (Q4_K_M) — bands, never points.
MoE: file is 164GB (that decides fit) but only ~18B of experts activate per token (~9.2GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math
→ rtx-3090 — the next step up from NVIDIA GeForce RTX 3080 Ti
→ every model the NVIDIA GeForce RTX 3080 Ti can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run