# Balancing Latency and Accuracy of Code Completion via Local-Cloud Model Cascading

arXiv: https://arxiv.org/abs/2603.05974 · HTML: https://mlsanity.com/paper/2603.05974/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2026.

## Built on by (most cited first, 1 of 1)

- [Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing](https://mlsanity.com/paper/2606.03618/) (2026)

## Abstract (arXiv)

Line-level code completion requires a critical balance between high accuracy and low latency. Existing methods suffer from a trade-off: large language models (LLMs) provide high-quality suggestions but incur high latency, while small language models (SLMs) are fast but often suboptimal. We propose MCCom (Model-Cascading-based code Completion), a framework that cascades a local SLM with a cloud-based LLM. To achieve effective cascading, MCCom leverages user actions as a novel signal to trigger the LLM only when the SLM fails, significantly reducing cloud computation costs. Furthermore, we introduce a two-stage speculative decoding strategy and an iterative retrieval mechanism to enhance collaboration between the models. We also train a 121M-parameter lightweight model, which achieves 73.8% of the performance of a 7B state-of-the-art model. Evaluated on RepoEval and a new real-world benchmark StmtEval, MCCom reduces inference latency by up to 47.9% and LLM usage by 46.3%, while improving the LLM's exact match rate by 8.9% through effective collaboration.