On-Device Language Model Fine-Tuning

On-device fine-tuning lets a large language model (LLM) learn from its user's private data without uploading it. Low-rank adaptation (LoRA) reduces the trainable parameters, but each first-order training step still multiplies by the frozen base-model weights during the forward pass, activation recomputation, and input-gradient computation. A phone's neural processing unit (NPU) already holds these weights for inference; using it for training also requires computing input gradients, which its inference interface does not support. We present a system that runs all three frozen-weight products on the NPU while keeping the training graph, adapters, and optimizer on the CPU. Its input-gradient kernels reuse the resident weight tiles and the forward dequantizer, avoiding a transposed weight copy and ensuring forward and backward use the same effective weights. To preserve usable gradients, the system selects precision by gradient sensitivity and applies a per-row range guard for half-precision (FP16) outputs. Its runtime fuses the remaining CPU operators and overlaps NPU execution with adapter computation, while resumable execution and thermal pacing let training proceed as a background job. We evaluate it on two Qualcomm Snapdragon platforms using four LLMs from the Qwen and Llama families. Our workloads cover nightly personalization with labels supplied on the phone and the public LaMP-2 benchmark; comparisons include an optimized CPU trainer, a phone-GPU trainer, forward-only training, and GPU-trained references.

Multi-billion-parameter LLMs now run on phones for inference, and training them on the device would personalize them without user data leaving the phone. Prior work has measured individual training steps of such models on phones, but not complete training runs, and not whether adapters trained on the device improve personalization. We present the first systematic characterization of a multi-billion-parameter LLM fine-tuned on a mobile device, covering memory, per-step time, thermal behavior, and energy. An iPhone 17 Pro can fine-tune a 3B-parameter LLM to a typical user within one battery charge, and the resulting adapters improve personalization as much as adapters trained on a server. Sustained training throttles the phone to about half its initial throughput, and none of the pausing or burst schedules we tested recovers it. Nearly all of each training step is spent in the frozen base model, most of it in the backward pass, which nine of the ten other runtimes we audited do not accelerate. Apple's MLX had a kernel for it that was never dispatched and was incorrect, and our repair, now merged upstream, trains an adapter 1.47x faster on a third less energy. On-device fine-tuning is feasible on current phones, and making it efficient requires runtimes and operating systems to treat training as a first-class workload.

Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter-mode setting, however, the adapter is more than a compact storage module; it introduces an additional dense floating-point branch, maintains a trainable state for local updates, and acts as a unit of communication and hot-swapping.We introduce LoRDBA, a LoRA-compatible adapter that replaces both low-rank factors with binary sign carriers while representing magnitudes through lightweight, channel-wise scales, converting the dense adapter branch into two sign-accumulation matrix multiplications interleaved with channel-wise scaling. A finite-sample analysis shows that reconstruction quality is governed by the residual-to-magnitude ratio of the original LoRA factors. In adapter-mode experiments, LoRDBA outperforms low-bit baselines at matched model sizes while matching fp16 LoRA quality in selected regimes. The unmerged adapter incurs at most 8% prefill latency overhead at matched rank r=16 despite an over 10x reduction in adapter footprint, with moderate training memory overhead of approximately 1.6x that of fp16 LoRA.

Federated fine-tuning offers a promising paradigm for adapting large language models (LLMs) on edge devices by leveraging the rich, diverse, and continuously generated data from smartphones and IoT devices without compromising user data privacy. Such edge-side adaptation can improve model personalization, robustness, and responsiveness to local contexts. However, the practical feasibility of federated LLM fine-tuning on real edge devices remains unclear, as most existing work focuses on cross-silo or simulation-based settings, overlooking the resource and runtime constraints that determine whether a method is deployable on real edge systems. We present EdgeFlowerTune, a deployment-oriented benchmark for federated LLM fine-tuning under realistic edge-system constraints. EdgeFlowerTune jointly evaluates model quality and system costs, including communication, wall-clock latency, memory usage, energy consumption, and robustness to dynamic edge conditions. To compare methods in terms of effectiveness, efficiency, and robustness, EdgeFlowerTune introduces three complementary protocols: Quality-under-Budget, Cost-to-Target, and Robustness. We instantiate EdgeFlowerTune as a real-device platform built on Flower and MobileFineTuner, spanning commercial Android smartphones and NVIDIA edge development boards. Our benchmark results show that accuracy-only evaluation can lead to misleading conclusions: methods with similar final quality may differ substantially in deployability once realistic system constraints are considered. EdgeFlowerTune provides a reproducible benchmark for system-aware evaluation of federated LLM fine-tuning at the edge.

Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach for adapting large language models (LLMs). However, despite reducing trainable parameter counts, many PEFT methods remain memory-bound by token-level activation intermediates that scale linearly with sequence length, limiting their practicality for long-context and on-device adaptation. Unlike prior memory-efficient PEFT approaches that preserve token-level adapter activations, LARS (Low-memory Activation-Rank Subspace) reduces the sequence-length scaling of stored adapter activation intermediates from O(BSRL) to O(BRL) by performing adaptation within a sequence-level low-rank subspace. Through pooled feature extraction, low-rank subspace modulations, and residual projection, LARS reduces the overall memory footprint by 23% on GPUs and 47.8% on CPUs relative to LoRA at S = 1024, with relative savings increasing with context length. Experiments across reasoning, understanding, long-context, retrieval, and token-level tasks show that LARS maintains competitive performance relative to LoRA while substantially improving memory efficiency. Beyond GPUs, LARS also reduces average CPU power and energy consumption per optimisation step by 22.43% and 22.06%, respectively. These results demonstrate that activation-efficient adaptation provides a practical path toward resource-constrained and on-device fine-tuning of LLMs.

More than half the global population now carries devices that can run ChatGPT-like language models with no Internet connection and minimal safety oversight -- and hence the potential to promote self-harm, financial losses and extremism among other dangers. Existing safety tools either require cloud connectivity or discover failures only after harm has occurred. Here we show that a large class of potentially dangerous tipping originates at the atomistic scale in such edge AI due to competition for the machinery's attention. This yields a mathematical formula for the dynamical tipping point n*, governed by dot-product competition for attention between the conversation's context and competing output basins, that reveals new control levers. Validated against multiple AI models, the mechanism can be instantiated for different definitions of 'good' and 'bad' and hence in principle applies across domains (e.g. health, law, finance, defense), changing legal landscapes (e.g. EU, UK, US and state level), languages, and cultural settings.

Quantization reduces the deployment cost of large language models (LLMs). However, post-training quantization (PTQ) cannot fine-tune model parameters and often degrades accuracy in low-bit settings, while quantization-aware training (QAT) requires backpropagation and incurs high memory overhead. We propose ZeroQAT, a zeroth-order QAT framework supporting both weight and activation quantization. By using forward-only gradient estimation, ZeroQAT removes backpropagation and substantially reduces memory and computation while retaining end-to-end optimization benefits. We further introduce a lightweight variant of ZeroQAT for quantized fine-tuning, which freezes and pre-quantizes most parameters to further cut memory usage. Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory. For example, ZeroQAT enables fine-tuning of a 13B model at extremely low bit-widths (e.g., 2-4 bits) on a single 8GB GPU, and even allows fine-tuning a 6.7B model on a OnePlus 12 smartphone, demonstrating its practicality for end-to-end QAT on resource-limited edge devices.