CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment

Paolo Astrino

CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment

Computation and Language 2026-02-04 v1

Authors: Paolo Astrino

Abstract

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.

Keywords

RAG foundation models memory efficiency retrieval-augmented generation GDPR compliance local deployment BEIR benchmarks

Cite

@article{arxiv.2602.03731,
  title  = {CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment},
  author = {Paolo Astrino},
  journal= {arXiv preprint arXiv:2602.03731},
  year   = {2026}
}

Comments

24 pages, 2 figures, 6 tables

CUBO: Self-Contained Retrieval-Augmented Generation on Consumer Laptops 10 GB Corpora, 16 GB RAM, Single-Device Deployment

Abstract

Keywords

Cite

Comments

Related papers