I benchmarked 13 models at 65K-128K context to find out what actually matters for agentic workloads

I benchmarked 13 models at 65K-128K context to find out what actually matters for agentic workloads — prefill dominates everything, and KV head count beats parameter count I've been running local LLMs for agentic workflows (tool use, coding agents, RAG) and kept seeing people obsess over tg128 (toke

中文全文翻译正在补齐，可先查看下方英文原文。

I benchmarked 13 models at 65K-128K context to find out what actually matters for agentic workloads — prefill dominates everything, and KV head count beats parameter count I've been running local LLMs for agentic workflows (tool use, coding agents, RAG) and kept seeing people obsess over tg128 (toke