On-Device Language Model Inference

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 229% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 111

Aug 13, 2026cs.AI

Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes

Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However, implementing cognitively capable agents in such environments is conceptually and technologically challenging. Among a range of blueprints and development approaches, the Cognitive Embodied Agent Architecture (CEAA) has been developed as an implementation-oriented framework for architecting components of perception, memory, reasoning, planning, and embodied action. Considering the recent advances in edge computing and generative AI language models, this paper explores the use of Small Language Models (SLMs) to support edge-based operation of selected CEAA components, focusing on "Think" and "Memory" as processes central to cognitive orchestration and persistence of virtual agents in interactive virtual worlds. An edge-based virtual agent gateway system was developed and evaluated on an NVIDIA Jetson Orin NX using Qwen2.5 models of different sizes, exploring the system's capability to process service requests and handle memory-driven conversations. A series of simulation experiments evaluated routing accuracy, memory-read performance, and latency, demonstrating an SLM-driven prototype agent system that partially implements selected CEAA processes to support the development of embodied agents whose cognitive "brain" can operate efficiently and contextually for interactive experiences in immersive virtual worlds.

Aimilios Hadjiliasi, Louis Nisiotis

Department of Computing, Engineering and Mathematics University of Central Lancashire, Cyprus

Cognitive Architectures for AI Agents On-Device Language Model Inference Small Language Models Embodied AI Memory-Augmented Agents

Aug 11, 2026cs.OS

MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive target model decoding steps. Its effectiveness depends heavily on draft selection, motivating adaptive methods that exploit variation across inputs and generation stages. On memory-constrained edge devices, however, these methods often fail to improve end-to-end throughput due to the overhead of switching between draft models. We identify a key limitation in this setting: the mismatch between draft selection and draft availability under tight memory budgets. To address this challenge, we present MemSpec, a prediction-guided, memory-aware runtime for adaptive speculative decoding on edge devices. MemSpec decouples draft selection from execution through proactive resident working-set management. A lightweight predictor estimates draft effectiveness from prompt and generation context, while a memory-aware scheduler reduces reactive model loading overhead. Experiments on a Jetson Orin Nano show that MemSpec improves steady-state generation throughput by 40.7% on average over state-of-the-art bandit-based adaptive methods while closely approaching the oracle upper bound.

Eunjeong Kim, Yeong Jun Jeon, Myeonggyun Han

Kyungpook National University Daegu, Republic of Korea

On-Device Language Model Inference LLM Inference Scheduling Memory-Efficient Inference Speculative Decoding

Aug 6, 2026cs.CL

GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization

Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into a privacy risk. Adversarial anonymization defends against this by rewriting a text with a capable language model that also plays the attacker, but it needs a powerful model at inference time and thus sends private text to a third party, the very exposure anonymization should prevent. Recent work distills this behavior into a small on-device model using supervised fine-tuning and direct preference optimization (DPO), but DPO only imitates the teacher's offline choices and never directly optimizes the privacy--utility objective we care about. We introduce \textbf{GRASP} (\textbf{G}roup-\textbf{R}elative \textbf{A}nonymization via \textbf{S}elf-refinement \textbf{P}olicy-optimization), which reinforces the local anonymizer online with Group Relative Policy Optimization. A single small model acts as anonymizer, adversary, and utility judge, trained against a self-generated reward that hides attributes while preserving meaning, with a design that guards against reward hacking. Trained on Llama-3.1-8B, \ours{} improves the privacy--utility trade-off over the DPO-distilled baseline, consistently across three independent LLM judges. Against adversarial anonymization driven by frontier models such as Gemini~~2.5~~Flash and Claude, it achieves a comparable or better overall trade-off while removing substantially more private information, and it runs entirely on-device at roughly

1\%

of the GPT-4o teacher's cost.

Sajjad Ghiasvand, Nader Sehatbakhsh

Electrical and Computer Engineering Department, UC Santa Barbara1 · Electrical and Computer Engineering Department, UC Los Angeles2

On-Device Language Model Inference Privacy-Preserving Language Models Privacy Leakage in Language Models

Aug 5, 2026cs.AR

EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding

On-device deployment of Large Language Models (LLMs) has become essential for personalized edge applications. A primary bottleneck is external memory access (EMA) in feed-forward network (FFN) layers. Speculative decoding and mixture-of-experts (MoE) are promising solutions. Speculative decoding reduces the number of decoding stages by generating multiple tokens per stage, and MoE minimizes per-stage cost through sparse expert activation. However, there is an incompatibility when combining these two techniques. We propose EdgeXpert, a software-hardware co-designed LLM accelerator that resolves this incompatibility. In the prefill stage, the prompt-wise expert reuse reformulates routing as prompt-level expert reuse rather than independent per-token expert selection. It identifies important tokens using a lightweight encoder, constructs a shared expert set from them, and routes less important tokens with a reduced expert budget to lower expert EMA. In the decode stage, depth-aware expert coalescing exploits the contextual similarity and mutual exclusivity of same-depth candidate tokens. Rather than loading the union of all required channels, EdgeXpert loads only salient channels and applies computational calibration to recover accuracy without additional memory access. Synthesized in Samsung 28nm technology at 800 MHz, EdgeXpert achieves up to 56.3% latency reduction and 44.1% energy reduction compared to prior works, while maintaining near-baseline accuracy.

Sangwoo Ha, Hyunwoo Seo, Yurim Jo +2

KAIST Daejeon, South Korea

AI Accelerator Inference On-Device Language Model Inference Mixture-of-Experts Inference Memory-Efficient Inference Speculative Decoding

Aug 5, 2026cs.CL

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs

Despite rapid advances in large language models (LLMs), deploying and personalizing them on resource-constrained devices remains impractical due to high VRAM, time, and energy costs. Parameter-Efficient Fine-Tuning (PEFT) of Small Language Models (SLMs) offers a promising alternative, yet few studies compare PEFT methods across architectures using both general and personalization benchmarks while accounting for energy consumption. We compare five fine-tuning approaches (Full Fine-Tuning, LoRA, LoRA+, QLoRA, and BitFit) on four SLMs from two families (Transformer-based: TinyLlama-1.1B, Qwen3-1.7B; SSM-based: Mamba-1.4B, Mamba-2-1.3B) across three GLUE tasks (SST-2, QNLI, STS-B) and three LaMP personalization tasks (LaMP-1, LaMP-2, LaMP-3). Each configuration is evaluated with the energy-focused NetScore-E and the memory-focused NetScore-M, the two variants that reflect the constraints binding on-device deployment. Methods are selected with a strict energy-first rule (highest NetScore-E, ties broken by NetScore#). LoRA+ achieves the highest NetScore-E in 19 of 24 configurations and the highest NetScore-M in 13 of 24, and is the selected method in 18 of 24. QLoRA, available only for the Transformer models, cuts peak finetuning VRAM by up to 3.9x relative to LoRA and therefore takes the best NetScore-M in 5 of the 12 Transformer configurations, although its de-quantization overhead leaves it selected in only one of them once energy decides. BitFit and full fine-tuning are almost never competitive on either variant, and TinyLlama-1.1B leads the energy-focused NetScore-E on five of the six benchmarks and the memory-focused NetScore-M on four. These results show that compact SLMs paired with PEFT provide a practical, energy-aware path to personalized on-device deployment, with the optimal method set by the dominant constraint: LoRA+ for energy and QLoRA for memory.

Kuanysh Akhmetzhanov, Jurn-Gyu Park

Department of Computer Science, Nazarbayev University, Astana 010000, Kazakhstan

Fine-Tuning On-Device Language Model Inference Memory-Efficient Fine-Tuning Energy-Efficient ML Small Language Models Personalized Language Models+2

Aug 3, 2026cs.LG

Structured Memory for Edge Language Models: Persistent Context and Corpus Retrieval via O(1) SSM State Injection

Retrieval-augmented generation (RAG) imposes a prefill cost proportional to retrieved context length, and -- with Transformer backbones -- a KV-cache that grows with each generated token. State-Space Models (SSMs) avoid the second cost by construction; we eliminate the first, collapsing prefill from

O(L_{context})

to

O(1)

per query. We introduce PRECOG (Pre-Computed Context Injection), a retrieval mechanism that exploits a property unique to SSMs: the fixed-size, position-agnostic recurrent hidden state is a complete summary of everything the model has read. PRECOG pre-encodes document corpora offline as SSM hidden states and injects the best-matching state directly at query time, bypassing in-context re-ingestion entirely. The same state-injection mechanism enables SMC (Structured Memory Consolidation): a hierarchical persistent memory with cognitive-domain clustering, an adjustable fidelity-vs-storage dial, and

O(1)

session initialization, which consolidates short-term episodic states into long-term semantic memory and fuses both with retrieved corpus states at query time. We demonstrate the system on TENNs-LLM, a 1.2B-parameter gated-SSM language model with a 192 KB hidden state. PRECOG matches in-context RAG answer quality, reducing prefill latency from

\sim

27 s to

<

6 ms on edge hardware -- a

\sim

4500

\times

speedup that crosses the threshold from unusable to interactive. The mechanism is architecturally impossible for Transformer KV-caches, which are position-entangled and grow linearly with context length.

Anusha Madan Gopal, Aras Pirbadian, Kristofor D. Carlson +2

BrainChip Inc. 23041 Avenida de la Carlota, Laguna Hills, CA

Retrieval-Augmented Generation On-Device Language Model Inference Memory-Augmented Language Models Persistent Memory for Language Models LLM Inference Acceleration State Space Models

Aug 2, 2026cs.CL

Opt.Gear Technical Report

We introduce OptGear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a dense model (1M, 270M, and 1B) with a context length of 64K. We designed a new hybrid architecture that combines a convolutional key-value gated mixer with local-global attention to reduce the KV-cache memory that tends to increase exponentially with long context. This architecture delivers up to X4.9 faster prefill and decoding speeds on the NPUs compared to models of a similar scale models. From a 2T tokens candidate corpus, OptGear is trained on a curated 0.5T tokens subset without knowledge distillation. This is the most data-efficient of the existing foundation models. All models are released with open weights and deployment binaries for ONNX, Qualcomm NPU, and Apple ANE making OptGear a practical base for edge applications that need fast, memory-efficient inference and strong task capabilities. Furthermore, to expand the ecosystem of on-device generative language models, we are introducing the OptGear-1M that can be deployed on Micro-Controller Units (MCUs), a Tiny Language Model (TLM). OptGear-1M is the first generative language model to achieve 20 TPS with W4A32 quantization on the ARM Cortex-M7 CPU of the STM32H747I-DISCO.

Juneyoung Park, Youngwook Kwon

Opt.Gear Team

On-Device Language Model Inference Long-Context Language Model Inference Small Language Models Attention Mechanisms

Aug 2, 2026cs.CR

CallScreenBench: Benchmarking On-Device Models as Phone Secretaries

Language models small enough to run on a handset, quantized to a few bits, are increasingly capable of acting for their user, making on-device task automation newly plausible. One such task is answering the phone. A phone secretary takes an unknown inbound call on its owner's behalf. Unlike the agents evaluated by most benchmarks, it has no task to complete and no cooperative user: the caller holds the goal, may be an adversary, and must be judged from the opening turn with no oracle. What matters is not task success, but whether the owner would endorse how their proxy handled the call. We present CallScreenBench, which scores this setting on five quality dimensions. Each dimension is printed beside the counter-metric that bills it and is never averaged into a single number. We also report a guardedness profile for a toolless proxy that holds no credentials and calls no tools. Across six on-device models (0.6-4B parameters, 4-bit quantization), quality scales with capability, but triage does not. The appearance that it does is an artifact of measurement. Scripted degenerate agents supply the missing floors: after correcting for them, the number of model pairs whose triage performance separates falls from 11 of 15 to zero at the preregistered operating point. An agent that simply hangs up and echoes the caller also scores perfect message fidelity. We report which of our own metrics these floors defeat and declare no pass/fail threshold.

Simiao Ren

On-Device Language Model Inference LLM Agent Evaluation AI Agent Benchmarks AI Agent Safety Benchmarks

Jul 27, 2026cs.CL

From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference

We present ELMOD - Efficient Language Model for On-Device Deployment - a compact (2.7B) German language model designed for efficient inference on resource-constrained hardware. ELMOD was trained on a limited computational budget (55k H100 GPU hours) using exclusively publicly available data. We developed a suite of German-specific data pre-processing, which differ from English-oriented counterparts in their handling of morphological variation, compounding, and orthographic conventions. Furthermore, we introduced a quality filtering and rephrasing step, which increased the instructional quality of the data, improved performance during the annealing phase, and reduced overall compute requirements. Thanks to our architectural model and data choices, including prefiltering, our educational-quality filtering and rephrasal to raise the educational-quality, ELMOD is the strongest performer in its size class (<3B), matching the performance of 7B-parameter models in German.

Darina Gold, Alexander Schwirjow, Viktor Haag +4

IIS Fraunhofer

On-Device Language Model Inference Training Data Curation Small Language Models Efficient Language Model Training Language Modeling

Jul 27, 2026cs.LG

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference

Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory. We target latency-critical single-user settings where routed experts are staged on demand from CPU memory to a GPU or from Flash to a mobile NPU. In this setting, self-speculative decoding faces a new bottleneck: increasing the draft expert set improves accuracy but triggers extra expert loading, while cheap small-footprint drafts have low acceptance; moreover, verifying a multi-token block activates the union of target experts and is no longer close to one target step. We propose DraftExpert, an expansion-aware self-speculative decoding framework for expert-offloaded MoE inference. DraftExpert trains one lightweight accelerator-resident draft expert per layer by self-distilling residual, logit/token, and router-agreement signals from the frozen target MoE. At inference time, it uses a fixed-footprint shared+top-1+draft-expert drafter together with confidence--expansion truncation and target-expert prefetching, while final tokens are still exactly verified by the target model. On DeepSeek-V2-Lite and Moonlight-16B-A3B across CPU-GPU and Flash-NPU offload, DraftExpert improves decode throughput by 1.45x on average, raises draft acceptance to 84~~87%, and achieves 86~~88% prefetch hit rates.

Dengke Han

Expert Offloading On-Device Language Model Inference Mixture-of-Experts Inference Speculative Decoding LLM Inference Acceleration

Jul 23, 2026cs.AI

Profiling Lightweight Large Language Models

Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resource-constrained edge and mobile environments. In such settings, energy consumption, execution time, and memory usage directly affect practical usability, yet existing evaluations of LLM efficiency largely rely on proxy descriptors such as parameter count or FLOPs, often decoupled from task precision. This paper introduces a PTME-based experimental framework for the precision-aware profiling of lightweight LLM inference, jointly measuring Precision, execution Time, peak Memory usage, and Energy consumption through direct hardware-level measurements. The methodology is applied to a representative set of lightweight LLMs executed locally under edge-class resource envelopes on a controlled desktop platform, using benchmarks spanning code generation, mathematical reasoning, and multi-task understanding. We find that static proxy descriptors approximate inference cost well but fail to predict precision. Tightening the resource envelope increases cost without affecting precision, amplifying execution time more strongly than energy and penalizing larger models the most. Moreover, no single model dominates across all PTME dimensions, and a Pareto analysis reveals non-dominated configurations that would be hidden by accuracy-only or efficiency-only assessments, providing practical guidance for selecting models under different resource envelopes. These results show that selecting lightweight LLMs by size, FLOPs, latency, or accuracy alone can select the wrong deployment candidate; PTME profiling exposes configurations that preserve useful accuracy at lower physical cost.

Tomohiro Harada, Enrique Alba, Gabriel Luque

Graduate School of Science and Engineering, Saitama University, Saitama, Japan

LLM Inference Efficiency LLM Evaluation On-Device Language Model Inference LLM Inference Small Language Models

Jul 21, 2026cs.AR

BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators

Apple's M5 generation introduces a redesigned GPU architecture in which every core carries a dedicated Neural Accelerator: on-die matrix units exposed through the Metal4 tensor API. We show that BaseRT, our native Metal inference runtime for large language models on Apple Silicon, exploits these units to push inference throughput on Apple hardware substantially beyond both llama.cpp and MLX. Building on BaseRT's framework-free design, we add a family of hand-written Metal4 tensor-core kernels (including dense and mixture-of-experts GEMM and flash-attention prefill kernels) that route the compute-bound matrix multiplications of inference through the M5 Neural Accelerators while leaving the memory-bound decode path on our existing specialised kernels. On an Apple M5 Pro, across fifteen model configurations spanning the Qwen3, Qwen3.5/3.6, Llama~~3.2, and Gemma~~4 families from sub-1B to 35B parameters, BaseRT delivers up to

6.4\times

higher prompt-processing throughput than llama.cpp and

3.9\times

higher than MLX, with the largest margins on the mixture-of-experts models where matrix multiplication dominates, while maintaining its lead on decode of up to

1.75\times

over llama.cpp and

1.33\times

over MLX. These results establish a new performance ceiling for on-device LLM inference and show that the M5's tensor cores are the decisive lever for prompt processing on Apple Silicon. BaseRT is publicly available at https://github.com/basecompute/baseRT.

Fabian Waschkowski, Prabod Rathnayaka, Lukas Wesemann

Base Compute, Melbourne, Australia

AI Accelerator Inference On-Device Language Model Inference LLM Inference Acceleration

Jul 20, 2026cs.LG

SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs

Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a neuron-level optimization framework that enables efficient LLM inference on edge devices through selective neuron loading and computation. By profiling and identifying both task-specific and general-purpose neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces memory footprint by selectively loading a subset of neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant neurons at runtime. Evaluation across multiple datasets shows that SelectInfer achieves significant reductions in memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices

Huzaifa Shaaban Kabakibo, Eric Schniedermeyer, Artem Burchanow +1

Department of Computer Networks, Paderborn University, Paderborn, Germany

On-Device Language Model Inference Memory-Efficient Inference LLM Inference Acceleration Conditional Computation

Jul 20, 2026cs.AI

AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models

Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests. While recent systems based on Large Language Models (LLMs) improve this capability, they often rely on heavyweight reasoning pipelines and cloud-based deployment, limiting their efficiency and suitability for resource-constrained environments, and raising privacy concerns. In addition, existing approaches provide limited support for stable long-term personalization. To address these issues, we present AdaHome, an adaptive smart home assistant designed for locally deployed small language models in smart home environments. Rather than applying complex reasoning uniformly, AdaHome introduces an intent-aware planning framework that dynamically routes commands either to straightforward prompt-based or lightweight reasoning-based components. For commands requiring interpretation, we adopt a Chain-of-Draft strategy to enable efficient and stable decision-making. To support personalization, we further propose a preference adaptation mechanism that learns from user feedback over time without requiring prompt augmentation or model retraining. We evaluate AdaHome against representative LLM-based baselines under a unified small model setting. AdaHome achieves substantially higher accuracy on direct commands (86.7%) while reducing latency by up to 3

\times

. Furthermore, it maintains competitive performance on ambiguous inputs with lower computational cost. In multi-turn scenarios, AdaHome achieves 88% preference consistency, compared to 52.5% for a prompt augmentation baseline.

Eu Jin Lim, Zhaoxing Li, Sebastian Stein

University of Southampton Southampton, United Kingdom

Adaptive Inference On-Device Language Model Inference Small Language Models LLM Routing Conversational Agents Preference Learning

Jul 19, 2026cs.AI

Lossless but Not Free: An Empirical Anatomy of Speculative Decoding on Consumer Hardware

Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a small draft model proposes

K

tokens autoregressively, the target model scores all of them in one batched pass, and a rejection-sampling rule provably preserves the target model's output distribution. We present a from-scratch, device-agnostic (CUDA/MPS/CPU) implementation and an empirical study across five draft/target backend configurations on a consumer Apple-silicon laptop. Distribution equivalence is verified at three levels, culminating in a two-sample test over roughly 9,200 real-model tokens per method (

χ^2 = 162.5

, dof

= 200

,

p = 0.976

) and exact greedy-sequence agreement. The best configuration reaches a measured

1.61\times

wall-clock speedup at

K=6

, on an acceptance profile declining from 69.7% at

K=1

to 37.8% at the optimum, while three of five configurations decelerate, either because the draft fails to out-speed a small target or because the quantized Metal backend executes "parallel" verification serially, an effect we isolate and quantify. The failures are as instructive as the successes: speculative decoding pays off only when verification is genuinely batch-parallel and the draft/target latency gap is real.

Param Chordiya

University of California, San Diego

On-Device Language Model Inference Speculative Decoding LLM Inference Acceleration Parallel Decoding

Jul 16, 2026cs.AI

SmartRAG: Native Graph-Based RAG for Mobile Device

Deploying large language models (LLMs) as personal assistants on mobile devices demands privacy, low latency, and offline availability, yet the computational cost of giant models clashes with strict edge-hardware budgets. We argue that this tension cannot be resolved by model compression alone; it requires decomposing on-device intelligence into complementary functional roles. We present SmartRAG, a fully on-device framework that organizes an intelligent assistant around four coordinated modules -- Perception, Memory, Focus, and Thinking. At the core of SmartRAG is EvoNER, a continually learnable named-entity recognizer that incrementally expands its label inventory through teacher-distilled updates, enabling the system to absorb previously unseen entity types without retraining the backbone LLM. Extracted knowledge is stored in MRGraph, a three-layer provenance-preserving knowledge graph, and retrieved at query time through a hybrid pipeline combining graph traversal, lexical matching, and dense semantic search. The on-device LLM is invoked only for high-value semantic operations -- labeling, planning, and answer synthesis -- keeping inference costs bounded. Experiments on four QA benchmarks (TriviaQA, Natural Questions, HotpotQA, MultiHopQA) show that SmartRAG with a quantized 1.7B-parameter backbone achieves multi-hop reasoning performance competitive with models up to 18

\times

larger, while running entirely on commodity smartphones within practical memory and latency envelopes.

Zhihan Jiang, Meng Li, Shenghao Liu +5

1Nanjing University · 2HUST · 3Southeast University

Named Entity Recognition On-Device Language Model Inference Memory-Augmented Language Models LLM Reasoning with Graphs Graph Retrieval-Augmented Generation Knowledge Graph Question Answering

Jul 16, 2026cs.LG

PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference

CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs. We present PolyQ, a CPU-oriented compiler/quantization co-design for activation-aware channel-wise bit allocation under a user-specified average-bit budget. PolyQ assigns per-channel bit-widths from

\{2,3,4,8,16\}

, then uses a compile-time model compiler to permute and cluster channels into bit-homogeneous blocks, generate SIMD- and LUT-compatible kernels, and merge compatible permutations across operators to keep layout regularization off the runtime path. This turns fine-grained budget fitting into a practical fractional-bit deployment method for CPU-only inference. Across Falcon-H1-3B, Llama2-13B, and Qwen3-32B on WikiText-2, PolyQ provides stable quality scaling from 3--6,b and improves perplexity by 2.4--32.1% over prior methods at a 3,b target. End-to-end measurements on three representative CPUs -- workstation, laptop, and mobile -- show that compiler layout regularization reduces activation reorder traffic by up to 70.8%, prefill latency and decode throughput scale nearly proportionally with the configured bit budget, and energy/token overhead stays below 2% relative to an optimized LUT-based back-end. These results show that fractional-bit CPU deployment is practical, predictable, and energy-efficient across diverse edge targets.

Hyunwoo Oh, Suyeon Jang, Hanning Chen +4

University of California, Irvine

Mixed-Precision Quantization LLM Quantization On-Device Language Model Inference LLM Inference Acceleration Neural Network Quantization

Jul 14, 2026cs.CR

Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy. Full cloud inference delivers strong computing power but exposes user prompts and dialogue data, while standalone on-device inference is unfeasible for most consumer and embedded edge devices. This paper presents a privacy-centric edge-cloud collaborative LLM inference framework built on endpoint-authenticated KV cache. Local endpoints handle input preprocessing, embedding computation, adaptive feature optimization, KV cache authentication, speculative decoding and low-dimensional model head calculation, while the cloud conducts authenticated decoder inference, KV cache management, token verification and high-dimensional vocabulary projection. Endpoints fuse partial outputs, apply language-adaptive masking and sample target tokens. All transmitted data and truncated logits are quantized and AES-GCM encrypted for privacy, with core lightweight modules, draft parameters and cache access policies kept local to avoid leakage. The framework supports heterogeneous devices including CPU-only, GPU-equipped and embedded devices via optimized streaming, batching and quantized ONNX deployment. Evaluations demonstrate that the framework reduces per-token latency by up to 46.1% and downlink payloads by up to 67.4% over baseline split inference, retaining comparable performance to full cloud inference.

Yi Li, Chen Li, Jiexiong Liu

KunlunMeta

On-Device Language Model Inference Privacy-Preserving Language Models LLM Inference Efficient Language Model Inference

Jul 11, 2026cs.DC

Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

Running large language models on consumer devices such as laptops and desktops is challenging because model weights often exceed GPU memory capacity, making offloading inference necessary to extend effective model capacity with CPU memory. Existing offloading systems, however, typically rely on coarse layer-level or expert-level scheduling, which overlooks substantial heterogeneity among tensors within the same layer and adapts poorly to changing hardware load conditions on such devices. This paper presents ATSInfer, a hybrid CPU-GPU inference system for consumer devices that performs offloading at tensor granularity. ATSInfer combines static tensor placement with load-aware dynamic transfer, and introduces asynchronous CPU-GPU coordination to efficiently schedule hardware storage, data movement, and computation across heterogeneous backends. We implement ATSInfer and evaluate it on representative consumer platforms using both dense and MoE models. Compared with existing systems, ATSInfer improves prefill throughput by up to 1.94

\times

and decode throughput by up to 3.29

\times

, while also increasing GPU utilization and making more effective use of PCIe bandwidth. These results show that ATSInfer can substantially improve the user experience of local LLM deployment on personal consumer devices.

Yangyijian Liu, Hongyi Ye, Mingyang Li +1

School of Computer Science, Nanjing University Nanjing, China

On-Device Language Model Inference LLM Inference Scheduling LLM Inference Acceleration

Jul 10, 2026cs.CL

Workload-Driven Optimization for On-Device Real-Time Subtitle Translation

This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints. These conditions limit the value of optimizations designed for long-context or high-throughput language-model serving. Starting from LMT-60-0.6B, preliminary profiling suggests that vocabulary projection becomes a more important decode-time cost after GGUF quantization reduces the relative cost of Transformer blocks. We replace the original 151k-token vocabulary with a 64k-token subtitle-domain tokenizer, migrate the embedding space, and adapt the model through embedding calibration followed by full supervised fine-tuning. On a fixed 500-example subset of the OpenSubtitles2024 test set, the LocalSubs achieves a 59.2% tie-excluded win rate against Google Translate under GPT-4o pairwise judging. Performance is strongest on short cues and declines as cue length increases. Preliminary Apple M2 Metal measurements on a 64k-vocabulary model show a 1.63

\times

speedup over a 151k-vocabulary profiling baseline. The raw benchmark configuration is incomplete, so the latency result is treated as preliminary.

Tsz-To Wong

National Yang Ming Chiao Tung University, Hsinchu, Taiwan

On-Device Language Model Inference Efficient Language Model Inference Machine Translation

Jul 9, 2026cs.AI

Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment

High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: comparable output at a fraction of the time and cost. We measure what that distillation actually delivers, per sub-task. Each news article is mapped to one JSON object with a short summary and five categorical labels. We distill an 8B reasoning teacher (deepseek-r1:8b) into a 0.6B student (Qwen3-0.6B; QLoRA, three seeds), and add two teacher controls: a same-size non-reasoning teacher and a larger managed pipeline. A blinded, reference-free, three-judge panel scores every arm against the full article, alongside two non-distillation baselines, few-shot prompting and constrained decoding. The student runs at about 0.8 s per article against the teacher's 39 s, and recovers 58% of the base-to-teacher gap on summary quality, beating its primary baseline (constrained decoding) by +16.8 points and few-shot prompting by a secondary +4.9. A same-size non-reasoning teacher trains a student no better than the untuned base, so the summary gain follows from the teacher's reasoning nature rather than its scale. Capabilities then split by teacher: the reasoning teacher transfers writing quality and the managed pipeline transfers label diversity, while a same-size instruction teacher's students stay more grounded on the 22 short, thin-source articles in the 93-item test set (74 versus 55 faithful), where the reasoning-lineage student fabricates. That grounding difference is a consistent ordering rather than a significant aggregate effect, and the subgroup is small, so we report it as a direction. Because no single engine wins every field, the deliverable is a per-field routing map for on-device enrichment.

Vinay Kumar Chaganti

independent researcher

On-Device Language Model Inference LLM Information Extraction Language Model Distillation Knowledge Distillation

Jul 6, 2026cs.DC

When Words Predict Workload

Standard distributed \ac{llm} schedulers rely on static token counts or rolling latency averages, making them susceptible to failures on statutorily constrained text. On \ac{epo} claims governed by Article 84 \ac{epc}, linguistic rigidity makes human and machine authorship statistically indistinguishable. Resolving this ambiguity mid-flight forces dynamic multi-model ensemble expansion, triggering unpredictable KV-cache and weight-allocation spikes that saturate consumer-grade edge GPU VRAM and cause severe \ac{oom} crashes. To prevent hardware collapse, we propose a CPU-side Linguistic Resource Forecasting (LRF) gateway. The gateway extracts a 16-dimensional text-structure vector and applies an XGBoost predictor to forecast trap-band membership. The resulting escalation probability (

\Pesc

) is evaluated against a dynamic, closed-form routing threshold (

\Tauroute(t)

) computed via real-time latency telemetry. Requests are safely routed to either a local Qwen2.5-7B edge worker or a remote contrastive ensemble (Qwen2.5 7B + 32B) on an NVIDIA H100 \emph{before} any edge GPU memory is allocated. In a 6,000-request live trial, the LRF gateway reduced the operational misroute fraction (

R_{\mathrm{mis}}

) to

0.087

--

0.095

, an order of magnitude below the token-count baseline (

0.849

). Peak edge VRAM remained safely bounded at

\SI{4.82}{\gibi\byte}

(under the

\SI{8}{\gibi\byte}

ceiling) across a

27\times

variation in \ac{wan} delay. The predictor achieved a live-trial AUROC of

0.84

, and the dynamic

\Tauroute(t)

controller yielded an

8.2\%

relative reduction in misroutes compared to an equivalent static threshold.

Anubhab Banerjee

Nokia Germany

On-Device Language Model Inference LLM Inference Real-Time Scheduling LLM Inference Scheduling LLM Routing LLM Request Scheduling

Jul 6, 2026cs.AR

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency. We present the first comprehensive, cross-layer measurement study of mobile LLM inference, uniquely spanning five mainstream frameworks (e.g., llama.cpp, GENIE) and three hardware backends (CPU, GPU, NPU). To enable this analysis, we develop PowerBench, a fine-grained profiling tool that provides the first backend-specific energy attribution, moving beyond traditional device-level measurements. Our study yields three critical insights: (1) Framework-induced performance gaps are substantially amplified on NPUs, reaching up to 10x using custom operators due to divergent offloading and quantization strategies. (2) We identify a distinct phase split where NPUs excel at compute-bound prefilling, while CPUs outperform all other backends in memory-bound decoding. This is driven by the NPU's preference for large, fixed-shape workloads, which conflicts with the small-kernel, dynamic nature of decoding. (3) Backend-specific profiling uncovers substantial scheduling headroom missed by prior work. Suboptimal thread configurations, uncoordinated NPU sleep latencies, and CPU polling intervals result in up to 40% energy waste. Leveraging these findings, we present an energy-oriented best-practice configuration for mobile LLM inference. We estimate that this configuration could reduce energy consumption by up to 54.8% on the NPU backend across three datasets.

Guanyu Cai, Ruiming Tian, Lang Yang +4

Tsinghua University · Beijing Jiaotong University

LLM Inference Efficiency AI Accelerator Inference On-Device Language Model Inference LLM Inference

Jul 6, 2026cs.OS

Elastic Gang: Per-Token Membership Change for a Hard-Barriered LLM Inference Gang Co-Scheduled with OS Processes

On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously. A barriered gang cannot simply be dropped into a preemptive scheduler: an unannounced departure deadlocks a barrier, and an unannounced arrival silently corrupts logits. I present the elastic gang of Anima OS, a bare-metal x86-64 Rust kernel in which the inference gang is a first-class schedulable entity whose core membership may change between any two tokens. The core mechanism is an ACK-latched epoch protocol that never waits on a named core: a seqlock-style generation-tagged latch composed with RCU/epoch-style membership consent, so each token's participant set is the intersection of the cores the gang requested and the cores that acked the current epoch. An un-acked core is outside this token and joins at most one token later. Displaced general processes migrate and keep running; cores return to them the moment a generation ends. On a real AMD Zen 5 machine (8C/16T), inference output is bit-exact under verified per-token membership change on both a 135M and a 7B model, the property that makes elasticity safe in a kernel whose safety gate reads logits. Against fair static core partitions, elastic membership Pareto-dominates: at intermediate inference duty cycles it delivers 1.75x (25%), 1.52x (50%), and 1.28x (75%) the general throughput of a static 8-core split at equal or better inference throughput, recovers all eight stranded cores when inference is idle, and converges to the split at saturation. Returning a lent core costs 0.22 us (p50); acquiring a busy, tenant-occupied core costs one scheduling quantum (~16 ms): a running tenant is never preempted mid-slice. Decode throughput saturates at gang width 8, so ceding cores past the knee is nearly free: elasticity auto-sizes the gang online.

Daeyeon Son

Independent Researcher · Republic of Korea

On-Device Language Model Inference

Jul 4, 2026cs.LG

AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference

With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations. Fixed-depth speculative decoding has emerged as one promising technique, but in practice, it often leads to performance degradation due to either bandwidth saturation, instability, or even catastrophic resource exhaustion resulting in system failure. To overcome this problem, we introduce AdaptiveSD, a fully runtime-adaptive speculative decoding framework aimed at ensuring robust, reliable execution across the spectrum of model types and workloads. Our solution consists of four tightly-coupled components working together in a continuous feedback loop: a Runtime Monitoring Engine tracking multiple signals relevant to ongoing computation, an Adaptive Draft Controller enforcing an eleven rule policy hierarchy prioritizing system resource preservation over raw draft count, a Dynamic Policy Engine employing a suite of heuristic and reinforcement learning techniques to dynamically modify policies depending upon workload behavior, and finally, a KV Cache Coordination Layer managing cache states with fine-grained control through INT8 shadow buffers and position aware evictions. While conventional approaches focus solely on maximizing throughput, we instead assess the effectiveness of our approach based on several key metrics including wasted drafted compute and inter-token latency dispersion alongside standard measures of speculative efficiency.

Sadra Saremi

Department of Physics, Iran University of Science and Technology, Tehran 16846-13114, Iran.

On-Device Language Model Inference Memory-Efficient Inference Speculative Decoding

Jul 3, 2026cs.LG

STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition

HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, cloud inference adds latency and privacy risk, and fine-tuned LLM pipelines turn general-purpose models into task-specific classifiers. We present STELLA, an efficient sensor-to-LLM translation framework for on-device HAR that shifts the burden from LLM adaptation to sensor tokenization. A lightweight hierarchical tokenizer compresses an entire multi-channel inertial window into a fixed set of compact latent sensor tokens, which are projected into the embedding space of a frozen pretrained LLM and combined with a natural-language prompt for label scoring. This preserves activity-relevant temporal and cross-channel structure while keeping LLM-side computation predictable across sensor configurations. STELLA also supports on-device personalization, adapting only the lightweight tokenizer on small amounts of user-specific labelled data and augmenting inference with a local retrieval context, keeping the LLM, user data, and retrieval on device. Across seven public HAR datasets and eight benchmark settings, STELLA achieves new state-of-the-art performance, improving over prior methods by up to 11.83% F1; on-device personalization yields up to a further 21.91% F1 as user data accumulates after deployment. STELLA also outperforms representative time-series tokenizers under the same LLM pipeline and achieves real-time inference under practical mobile and edge budgets, showing that efficient sensor tokenization is a practical path toward accurate, private, and personalized LLM-based HAR on edge devices.

Nirhoshan Sivaroopan, Albert Zomaya, Kanchana Thilakarathna

The University of Sydney · Australia

On-Device Language Model Inference Human Activity Recognition

Jul 1, 2026cs.CL

BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal

We present BaseRT, a native Metal inference runtime for large language models (LLMs) on Apple Silicon, and report the highest inference throughput on this hardware to date. Existing runtimes, including llama.cpp and MLX-based frameworks, incur overhead from abstractions not designed for Metal's execution model or Apple Silicon's unified memory topology. By building natively on Metal with chip-specific kernel fusion, unified memory-aware optimisation, and custom dispatch logic, BaseRT recovers performance that framework-based approaches leave on the table. BaseRT supports a wide range of model families across eight quantisation formats (Q2 to FP16) on all Apple M-series devices. In this paper, we evaluate the Qwen3, Llama 3.2, and Gemma 4 families at Q4 and Q8 quantisation on M3 and M4 Pro devices. BaseRT achieves up to 1.56x higher decode throughput than llama.cpp and up to 1.35x higher than MLX, with substantially larger margins on prefill for mixture-of-experts models, delivering consistent best-in-class throughput from sub-1B to 30B parameter models. These results establish Apple Silicon as a more capable inference platform than previously reported, with direct implications for the emerging edge inference paradigm: as privacy requirements, latency constraints, and cloud cost pressures drive inference toward on-device deployment, performance-optimised local runtimes are a critical enabling layer for this transition. BaseRT is publicly available at https://github.com/basecompute/baseRT

Prabod Rathnayaka, Fabian Waschkowski, Lukas Wesemann

Base Compute, Melbourne, Australia

AI Accelerator Inference On-Device Language Model Inference LLM Inference Acceleration

Jun 29, 2026cs.CL

Little Brains, Big Feats: Exploring Compact Language Models

While large language models have been dominating the research landscape recently, small language models remain highly relevant across various domains; yet, they receive far less attention. In this study, we investigate how smaller language models perform during the generation stage within a Retrieval-Augmented Generation (RAG) system. To benchmark these models effectively, we utilised both open-source and proprietary datasets covering diverse subject areas and question types. Our findings demonstrate that a RAG system with small language models can be executed directly on-device without requiring any GPU hardware within a reasonable time. The experimental code and links to the supplementary materials can be accessed through the GitHub repository: https://github.com/SibNN/SLM-RAG-EVAL.

Dari Baturova, Elena Bruches, Ivan Chernov +3

Siberian Neuronets LLC, Novosibirsk, Russia

Retrieval-Augmented Generation On-Device Language Model Inference Language Model Generation Evaluation Small Language Models

Jun 28, 2026cs.CL

MAM-AI: An On-Device Medical Retrieval-Augmented Generation System for Nurses and Midwives in Zanzibar

Maternal and newborn mortality remain among the highest in sub-Saharan Africa, where midwifery care is often delivered by nurses who lack midwifery training to international standards, and consulting authoritative guidance at the point of care is hard: the guidelines are long and connectivity is intermittent. We present MAM-AI, a medical question-answering assistant for nurse-midwives in Zanzibar that runs entirely on a commodity Android device: a question is embedded (EmbeddingGemma, 300M) and matched against a curated corpus of 87 guideline documents (63,650 passages), then answered with citations by a 4B int4 generator (Gemma 4 E4B), fully offline, with no query leaving the device. We evaluate the exact deployed configuration with a layered methodology -- retriever, generator under oracle context, end-to-end, and latency -- scored by LLM judges validated against physician rubrics. The evaluation relocates the hard problem. On-device retrieval is essentially solved: the 300M embedder ranks third of seven retrievers and rivals cloud systems, so the passages the system needs are usually found. The small generator is what remains in doubt: adding retrieved context does not improve its answers, and at 4B it cannot be both helpful and safe at once -- of two same-size candidates, the more helpful one commits genuine dangerous errors, so we deploy the other, which is about twice as faithful to its sources (as faithful as a frontier model), and recover its helpfulness with a redesigned prompt that cuts deflection from 33% to 3%. Corpus quality is decisive for the same reason: where the corpus holds the right passage the answer is specific and actionable, and where it does not it goes vague. MAM-AI is a thoroughly evaluated, open-source research prototype, not a fielded product; the system, knowledge base, benchmarks, and evaluation harness are released.

Yi Ren

École Polytechnique Fédérale de Lausanne, Switzerland

Retrieval-Augmented Generation On-Device Language Model Inference Clinical QA RAG Evaluation

Jun 25, 2026cs.CL

Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT

Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importance estimation, and their cross-architecture behavior remains unpredictable. This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order, with lightweight low-rank recovery between stages to re-estimate component importance. An information-theoretic analysis motivates this ordering, and the Structural Independence Assumption (SIA) is formalized as a checkable condition predicting whether per-component pruning criteria are reliable for a given architecture: Multi-Head Attention (MHA)+GELU designs satisfy the SIA, whereas Grouped Query Attention (GQA)+SwiGLU designs violate it. On bearing fault diagnosis spanning 88M to 6.25B-parameter models, the framework extends achievable compression to 13.8 times on MHA+GELU architectures with 83.82% accuracy (+3.70 percentage points (pp) over the strongest baseline), while exposing a ~74pp accuracy collapse on GQA+SwiGLU architectures that violate the SIA. Deployed on an industrial slewing bearing fault diagnosis platform with NVIDIA DGX Spark, compressed models reduce inference latency by up to 67.2% and peak memory by 62.5%, demonstrating viability for IIoT edge inference.

Jinghan Wang, Yanjun Chen, Wei Zhang +3

School of Mechanical and Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China · School of Information Science and Technology, Eastern Institute of Technology, Ningbo, China

LLM Pruning On-Device Language Model Inference Internet of Things Structured Pruning