The paper investigates how well common large‑language‑model (LLM) inference optimizations perform on Apple Silicon compared to server‑class NVIDIA GPUs. Four optimization families—KV‑cache pruning, speculative decoding, ported GPU kernels, and post‑training quantization—are evaluated on four Apple machines under a single‑request decode workload, with matched RTX 4090 comparisons where possible. Results show that KV‑cache pruning can boost Apple throughput up to 1.75×, while speculative decoding actually reduces throughput on Apple; CUDA kernel designs transfer only partially, and quantization gains vary by machine, indicating that speedups depend on the specific technique, runtime, hardware, and workload regime.
arXiv:2603. 23640v2 Announce Type: replace-cross Abstract: Deploying large language models on-device for always-on personal agents demands sustained inference from hardware tightly constrained in power, thermal envelope, and memory.
arXiv:2607. 00501v1 Announce Type: cross Abstract: 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.
arXiv:2605. 23057v2 Announce Type: replace Abstract: RequestRouter is a lightweight request-boundary controller for reducing the latency and energy cost of single-GPU large language model inference.
arXiv:2608. 01563v1 Announce Type: new Abstract: Training and deployed inference often cross export, conversion, and platform-specific runtime boundaries.
arXiv:2608.28667v1 Announce Type: cross Abstract: The rapid proliferation of Large Language Models (LLMs) has raised concerns about their environmental impact during inference. While Green AI researc...
The paper reports a reproducible GPU power benchmark for 18 open‑source LLMs (0.5B–7B parameters) run on a single consumer RTX 4060ti GPU using the Ollama inference engine. Energy metrics such as mean/peak power, total energy per prompt, energy per output token, and throughput were measured, revealing that model architecture and quantization strategy, rather than parameter count alone, drive energy efficiency. The most efficient models were qwen2.5:0.5b and tinyllama:1.1b, while the 7B‑Mistral model consumed up to 8.6× more energy per token, and qwen3.5:0.8b(on) showed unusually high per‑prompt energy due to extended internal reasoning.
arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.
arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.
arXiv:2608.28044v1 Announce Type: cross Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
arXiv:2610.17531v1 Announce Type: cross Abstract: While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting imp...
arXiv:2607. 05475v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency.
arXiv:2609.09662v1 Announce Type: cross Abstract: Deploying Large Language Models (LLMs) directly on mobile platforms at the edge is gaining traction due to a myriad of benefits, such as increased pr...