> articles

Articles

Notes from building with AI: local models, agents, and the systems around them.

Oct 13, 2026·5 min read
Breaking the Latency Wall: Optimizing MLX and Qwen for Local AI Agents on Apple Silicon
Why your local coding agent stalls on simple terminal commands, how Speculative Decoding breaks the KV cache in MLX, and how to configure your stack for subsecond responses.
- local-ai
- mlx
- apple-silicon
- agents
- qwen