# Deploying the CLIP vision encoder to the RK3588 NPU: notes on export, RKNN conversion, and mixed quantization

- Source: Guyuehome
- Published: 2026-10-29T06:33:00.000Z
- RoboHot: https://robohot.news/en/items/geuouwoyz49lm9p9h697zancl
- Original: https://www.guyuehome.com/detail?id=2111412950892834817

## Summary

The author documents the full process of deploying the CLIP vision encoder to the RK3588 NPU, covering model export, conversion to RKNN, and mixed quantization, and collects the problems encountered along the way. The material provides only a summary and does not give specific quantization configurations or performance data.