EmbBERT: Attention Under 2 MB Memory

TL;DR

EmbBERT is a highly efficient transformer model designed for ultra-constrained devices, achieving competitive NLP performance within just 2 MB of memory through architectural simplifications and quantization.

Contribution

This paper introduces EmbBERT, a novel tiny language model optimized for extreme memory constraints, demonstrating effective NLP performance with only 2 MB of memory.

Findings

EmbBERT requires only 2 MB of memory and matches state-of-the-art accuracy.

EmbBERT outperforms similar-sized downsized models like BERT and MAMBA.

Quantization reduces memory usage to 781 kB without significant performance loss.

Abstract

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements still hinder deployment on ultra-constrained devices such as wearables and Internet-of-Things (IoT) units, where available memory is limited to just a few megabytes. To address this challenge, we introduce EmbBERT, a tiny language model (TLM) architecturally designed for extreme efficiency. The model integrates a compact embedding layer, streamlined feed-forward blocks, and an efficient attention mechanism that together enable optimal performance under strict memory budgets. Through this redesign for the extreme edge, we demonstrate that highly simplified transformer architectures remain remarkably effective under tight resource constraints. EmbBERT requires only 2 MB of total memory, and achieves accuracy performance comparable to the ones of state-of-the-art (SotA) models that require a $\mathbf{10\times}$ memory budget. Extensive experiments on the curated TinyNLP benchmark and the GLUE suite confirm that EmbBERT achieves competitive accuracy, comparable to that of larger SotA models, and consistently outperforms downsized versions of BERT and MAMBA of similar size. Furthermore, we demonstrate the model resilience to 8-bit quantization, which further reduces memory usage to just 781 kB , and the scalability of the EmbBERT architecture across the sub-megabyte to tens-of-megabytes range. Finally, we perform an ablation study demonstrating the positive contributions of all components and the pre-training procedure. All code, scripts, and checkpoints are publicly released to ensure reproducibility: https://github.com/RiccardoBravin/tiny-LLM.