Challenge: MobileLLM-Flash is a family of foundation models for efficient on-device use with strong capabilities.
Approach: They propose a method for designing on-device large language models under mobile latency constraints using hardware-in-the-loop architecture search.
Outcome: The proposed model is amenable to industry-scale deployment and is compatible with mobile runtimes like Executorch.

Similar Papers

Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM (2026.findings-acl)

Copied to clipboard

Challenge: a framework for efficient on-device inference of large language models is needed for smartphones . memory, latency, and runtime flexibility are constraints for large language model deployments.
Approach: They propose a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model for Samsung Galaxy S24 and S25 devices with SM8650 and SM8750 chipsets respectively.
Outcome: The proposed framework improves memory, latency and performance across 9 languages and 8 tasks.
LLM in a flash: Efficient Large Language Model Inference with Limited Memory (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have high computational and memory requirements, especially for devices with limited memory.
Approach: They propose a method that stores model parameters in flash memory but brings them on demand to DRAM . authors propose two techniques to optimize for reading data in larger, more contiguous chunks .
Outcome: The proposed method reduces the volume of data transferred from flash and reads data in larger, more contiguous chunks.
MobileQuant: Mobile-friendly Quantization for On-device Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized language processing, but deployment on edge devices is costly in terms of memory, computation and energy.
Approach: They propose to reduce the number of bits used to represent weights and activations . they propose to use 8-bit activations to enable LLMs to fully exploit mobile-friendly hardware .
Outcome: The proposed method reduces the number of bits used to represent weights and activations . 8-bit activations are attractive for on-device deployment as they would exploit mobile-friendly hardware .
EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) driven by scaling laws can be developed in large model sizes.
Approach: They propose a pruning-aware pretraining approach that decouples LLM pruning from direct pretraining.
Outcome: The proposed model outperforms pretraining models with 100M 1B parameters in commen sense benchmarks.
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands .
Approach: They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices.
Outcome: Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.
LinguaLinked: Distributed Large Language Model Inference on Mobile Devices (2024.acl-demos)

Copied to clipboard

Challenge: Recent research shows that large language models demonstrate enhanced capabilities in various language tasks.
Approach: They introduce a system for decentralized, distributed LLM inference on mobile devices . they use optimized model assignment technique to segment LLMs and linear optimization to align segments with each device .
Outcome: The proposed system performs well on high-end to low-end Android devices.
Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing work on memory-efficient on-device fine-tuning of large language models with backpropagation has focused on approximating gradients with zeroth-order optimization (ZO).
Approach: They propose a memory-efficient implementation of backpropagation on mobile devices that allows flexible trade-offs between memory usage and compute time while converging faster.
Outcome: The proposed method can fine-tune LLMs with backpropagation using less than 1GB of memory while achieving better performance than the baseline.
Scaling Down, Serving Fast: Compressing and Deploying Efficient LLMs for Recommendation Systems (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications.
Approach: They propose two techniques for training and deploying small language models that deliver high performance for a variety of industry use cases.
Outcome: The proposed techniques retain much of the quality of larger models while reducing training/serving costs and latency.
ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models impose significant computational and storage burdens on personal devices . existing customization approaches incur excessive computational costs or lead to suboptimal performance .
Approach: They propose a training framework that converts pre-trained LLMs into parameter-sharing MoE models for lightweight deployment.
Outcome: The proposed training framework outperforms state-of-the-art training frameworks at the same sparsity level while delivering up to 2.71 inference speedup.
LLMs on a Budget? Say HOLA (2025.emnlp-industry)

Copied to clipboard

Challenge: Current solutions such as quantization, pruning, and Retrieval-Augmented Generation (RAG) offer only partial optimizations and often sacrifice accuracy, speed, or generality.
Approach: They propose an end-to-end optimization framework for efficient LLM deployment . it leverages Hierarchical Speculative Decoding (HSD) for faster inference without quality loss.
Outcome: HOLA delivers +17.6% EMA on GSM8K, +10.5% MCA on ARC, and reduced latency and memory on edge devices like Jetson Nano.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations