Field notes

Tutorials

Step-by-step tutorials for deploying, serving, and evaluating open-weight models — Kimi K3, GLM-5.2, DeepSeek — on infrastructure you own.

tutorialSeptember 18, 20266 min read

GLM-5.3-Flash and Qwen3.8-Flash-Next: Benchmark MTP Before You Deploy

Benchmark MTP for GLM-5.3-Flash and Qwen3.8-Flash-Next with pinned builds, memory checks and task-level acceptance gates.

MTPGLM-5.3-FlashQwen3.8-Flash-Nextllama.cppinference optimization

Start with the sovereignty assessment.

Two weeks, fixed fee. We map your data obligations and workloads, size the hardware, and hand you a written architecture with a real cost model — whether or not you build with us.

Book a sovereignty assessment Send me the TCO model or book a 20-minute call →