blogHuman Learning27 Aug 2026
I Tried Open Weight Models to Cut My AI Bill to Zero
Your AI product is an overnight success BUT your AI bills is giving you a heartache.
Aishwarya Raghavan
humanlearning.substack.com
mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
Categories
Articles
All articlesMore in Local Inference
View all toolsA
Aithy
Aithy is a private local AI runtime for state-of-the-art agent research, local inference, sandboxed tools, durable memory, and LAN Mesh resource sharing.
Atomic Chat
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.
C
Colibri
Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦