# Cline details tricks behind 11,840 tps on a single GPU

> Original title: We wrote more about the tricks we used and the future of local models and agentic inference here:

- Source: Cline
- Published: 2026-10-29T19:13:55.000Z
- Bad Influence: https://badinfluence.news/items/nbikxl4e11f7ua6m9k1edcl1k
- Original: https://x.com/cline/status/2115884856064479702

## Summary

Cline published a blog post describing the optimizations it used to reach 11,840 tokens per second on a single GPU. The post also covers the future of local models and agentic inference.

## Post

We wrote more about the tricks we used and the future of local models and agentic inference here:
https://cline.bot/blog/11-840-tps-on-a-single-gpu