CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment
It addresses the need for local, GDPR-compliant AI processing for organizations handling sensitive documents, offering a practical solution for small-to-medium archives.
The paper tackles the problem of deploying retrieval-augmented generation (RAG) on consumer laptops with limited memory by introducing CUBO, a system that achieves competitive Recall@10 scores (0.48-0.97 across BEIR domains) within a 15.5 GB RAM limit and retrieval latencies of 185 ms.
Organizations handling sensitive documents face a tension: cloud-based AI risks GDPR violations, while local systems typically require 18-32 GB RAM. This paper presents CUBO, a systems-oriented RAG platform for consumer laptops with 16 GB shared memory. CUBO's novelty lies in engineering integration of streaming ingestion (O(1) buffer overhead), tiered hybrid retrieval, and hardware-aware orchestration that enables competitive Recall@10 (0.48-0.97 across BEIR domains) within a hard 15.5 GB RAM ceiling. The 37,000-line codebase achieves retrieval latencies of 185 ms (p50) on C1,300 laptops while maintaining data minimization through local-only processing aligned with GDPR Art. 5(1)(c). Evaluation on BEIR benchmarks validates practical deployability for small-to-medium professional archives. The codebase is publicly available at https://github.com/PaoloAstrino/CUBO.