I've been using both K2.6 and K2.7 for software engineering over the past few weeks, primarily through OpenCode.
K2.7 is a noticeable improvement for coding. It follows complex instructions better, produces cleaner code, and feels more reliable during agentic development workflows.
One area where it really impressed me was GitHub pull request code reviews. I tested it on a core TypeScript project, and the review quality was genuinely strong. It caught meaningful issues, provided useful suggestions, and understood the broader context of the changes instead of focusing only on superficial style comments.
The OpenCode integration is also excellent. The overall experience feels smooth and natural, making it easy to use K2 as part of a real development workflow.
When starting an entirely new project from scratch, I still think Claude Opus 4.8 has an advantage. However, for an open-source model, K2.7 exceeded my expectations by a wide margin. It's one of the most capable open models I've used, and I'll definitely keep using it.
For a 3T-class open model the serving economics decide adoption more than the benchmarks. What is the activated parameter count per token, and what hardware footprint gives a usable tokens-per-second on a single node? That is the number bring-your-own-cloud teams will care about. Strong launch.
A browser extension version would be huge, so I can highlight text on any page and ask Kimi to explain or fact-check it without switching tabs. That alone would make it my daily driver.