A rented two-GPU box runs one capable model today. The question is not which bigger model to buy, but how many brains the same hardware can serve — and what each one costs. The constraint is video memory, not speed; the cost per user collapses as the machine fills up.
The box cost is fixed. Cost per user is simply $350 ÷ brains served. Optimisation lowers the cost by raising the denominator.
Cloud cost is flat per user. Local cost per user is a falling curve. They cross around 7 users.
The "1–2 users" figure only holds at full 256K context each. Shrink the context per slot and concurrency multiplies.
Weights, the per-user KV cache (working memory of context), and overhead all draw from the same 48 GB.
89 tok/s is not a fixed pie sliced across users. Single-stream is memory-bandwidth bound; with batching the weights load once and serve everyone, so aggregate throughput rises with concurrency.