The study examines how different weight encodings—dense fp16, int8, and ternary with two‑bit lookup tables—affect the placement and performance of language models on Apple’s Neural Engine (ANE) via Core ML. Using five checkpoints across two architectures, the authors combine compiler plans, memory‑controller measurements, and compute‑unit controls to assess a single‑token forward workload. Results show that fp16 models may run on the CPU or ANE depending on size, while compressed int8 models consistently activate the ANE and halve warm‑forward latency, demonstrating that encoding influences both placement and speed.
arXiv:2607. 24434v1 Announce Type: cross Abstract: 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.
The paper argues that AI deployment performance depends on interactions among compression, compiler transformations, and serving policies rather than just model architecture. It introduces a three‑layer taxonomy—model‑level techniques, compiler transformations, and system policies—and frames deployment as a constrained multi‑objective optimization problem over accuracy, latency, throughput, memory footprint, and energy. The authors propose an evidence protocol for comparable benchmarking and synthesize data from edge and data‑center platforms to show that cross‑layer interactions drive deployment outcomes, concluding with a constraint‑aware selection procedure and open research problems.
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.
arXiv:2607. 09385v1 Announce Type: cross Abstract: The growing adoption of large language model-based agents within operating system workflows has increased the importance of energy-efficient inference on laptop-class systems-on-chip (SoCs).
The paper introduces Routide, a Swift/MLX runtime that runs a quantized Qwen3.6-35B-A3B model on iPhone by keeping expert weights on device storage and a byte‑budgeted subset in memory. It evaluates cache‑policy effects, showing that a 512 MiB LRU cache yields 0.00% demand hits while a 576 MiB LRU reaches 38.58% hits across five 128‑token workloads, indicating that capacity limits depend on policy and workload. The study also reports memory footprints, thermal events, and power estimates, demonstrating that flash‑backed MoE inference is feasible within bounded resources but has measurable limitations.
arXiv:2607. 20806v1 Announce Type: new Abstract: 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.
arXiv:2606.03026v2 Announce Type: replace-cross Abstract: Binary spike activations allow a language-model runtime to read only active weight columns and replace multiplications by weight sums. We imp...
FlexEE is an early‑exiting framework designed for large language model inference that is constrained by computation and memory, particularly in offloading‑based deployments. It uses layer‑wise exit supervision, self‑speculative decoding over a Top‑K local vocabulary, and dynamic hidden‑state management to enable reliable intermediate‑layer predictions and memory‑aware execution. Experiments on Llama2‑7B and Llama3‑8B show that FlexEE achieves significant speedups—up to 1.27×/3.16× and 1.25×/2.83× respectively—while maintaining minimal accuracy loss.
arXiv:2609.17475v1 Announce Type: new Abstract: Capable open-weight models make local coding and reasoning attractive, but their context and execution state strain laptop memory. We present JustFit,...
arXiv:2605. 25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation.
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.
arXiv:2609.26333v1 Announce Type: new Abstract: Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce me...