can it run
14.2 GB vs 8 GB usable — does not fit
8GB · Ada · model file 14GB · 20B MoE
computed roofline: 272 GB/s × 0.55–0.88 efficiency window / 2.1GB (Q4_K_M) — bands, never points.
MoE: file is 14GB (that decides fit) but only ~3B of experts activate per token (~2.1GB streamed) — band below is the active-expert estimate, optimistic; community MoE rows run several× the naive bandwidth math
→ Tesla P40 (24GB, used) — cheapest catalog machine that runs gpt-oss 20B MoE fully ($290)
→ rtx-4060-ti-16gb — the next step up from NVIDIA GeForce RTX 4060
→ every model the NVIDIA GeForce RTX 4060 can run — full list
→explore the full catalog84 machines indexed · live prices · what each one can run