ModelDock technical insights
How local AI systems behave under real work.
Short, practical notes on the interactions among model runtime, context, hardware, and agent behavior. These are explanatory frameworks, not substitute benchmark claims.
Insight library
Technical reasoning, kept separate from the measurements.
Benchmark data remains on the Benchmark and Data pages. Insights explain what those measurements may mean for a real workload.
Bigger, but Slower: Optimal Context Windows for LLM Agents
A framework for choosing when an agent should compact context, based on observed prefill behavior and reconstruction cost.
Technical note · performance modelRead insight →