AWSBee

Blog

Notes on running open models in production

GPU sizing, inference cost and operations, from what we learn building the platform.

November 16, 2026 · 6 min read

How much GPU memory does an LLM actually need?

Model weights are only part of the bill. A simple way to estimate weights, KV cache and overhead before you pick a GPU.

Read article →

November 13, 2026 · 5 min read

When does self-hosting an open model beat a hosted API on cost?

Per-token pricing is simple until volume grows. How to compare an hourly GPU with a per-token bill, and where the break-even sits.

Read article →

November 10, 2026 · 4 min read

One OpenAI-compatible endpoint for every open model

Why a single gateway with one set of keys makes it easier to test, swap and govern models across teams.

Read article →