Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2603.23640

LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load

Pranay Tummalapalli·Sahil Arayakandy·Ritam Pal·Kautuk Kundan
View original source ↗Read source document ↗Export metadata ↓

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. We benchmark Qwen 2.5 1.5B (4-bit quantised) across four platforms: a Raspberry Pi 5 with Hailo-10H NPU, a Samsung Galaxy S24 Ultra, an iPhone 16 Pro, and a laptop NVIDIA RTX 4050 GPU. Using a fixed 258-token prompt over 20 warm-condition iterations per device, we measure throughput, latency, power, and thermal behaviour. For mobile platforms, thermal management supersedes peak compute as the primary constraint: the iPhone 16 Pro loses nearly half its throughput within two iterations, and the S24 Ultra suffers a hard OS-enforced GPU frequency floor that terminates inference entirely. On dedicated hardware, distinct constraints dominate: the RTX 4050 is bounded by its battery power ceiling, while the Hailo-10H is limited by on-module memory bandwidth. The RTX 4050 sustains 131.7 tok/s at 34.1 W; the Hailo-10H sustains 6.9 tok/s at under 2 W with near-zero variance, matching the RTX 4050 in energy proportionality at 19x lower throughput. Results should be interpreted as platform-level deployment characterisations for a single model and prompt type, reflecting hardware and software combined, rather than general claims about hardware capability alone.

Explore related subjects

cs.DCcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Pranay Tummalapalli, Sahil Arayakandy, Ritam Pal, Kautuk Kundan. 2026-06-07. LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load. https://arxiv.org/abs/2603.23640

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation

Graph Neural Networks (GNNs) have been widely adopted for their ability to compute expressive node representations in graph datasets. However, serving GNNs on large graphs is challenging due to the high communication, computation, and memory overheads of constructing and executing computation graphs, which represent information flow across large neighborhoods. Existing approximation techniques in training can mitigate the overheads but, in serving, still lead to high latency and/or accuracy loss. To this end, we propose Reforge, a system that enables low-latency GNN serving for large graphs with minimal accuracy loss through two key ideas. First, Reforge employs selective recomputation of precomputed embeddings, which allows for reusing precomputed computation subgraphs while selectively recomputing a small fraction to minimize accuracy loss. Second, we develop computation graph parallelism, which reduces communication overhead by parallelizing the creation and execution of computation graphs across machines. Our evaluation with large graph datasets and GNN models shows that Reforge significantly outperforms state-of-the-art techniques.

cs.DC↗
arXiv2026

Agentic AI Workload Characteristics

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the LLM-serving and tool-execution perspectives using an end-to-end tracing infrastructure across reasoning and non-reasoning Gemma and Qwen configurations on five agentic benchmarks. Our study shows that agentic workloads are not simply long-prompt workloads: with effective context caching, most input tokens are reused across turns, making execution decode-dominated while increasing dependence on long-lived KV-cache state. We also find that tool use has a clear temporal structure, with agents shifting from read/explore behavior early in execution to execute/write behavior later. These results show that efficient agentic serving must jointly manage repeated model re-entry, persistent context state, and workload-dependent tool behavior.

cs.DC↗
arXiv2026

Byzantine Causal Reliable Broadcast (BCRB) with Constant-Size Message Metadata

Asynchronous Byzantine Reliable Broadcast (BRB) is a fundamental primitive that guarantees agreement and validity in distributed systems subject to Byzantine faults, but it lacks ordering guarantees. In this paper, we address Byzantine Causal Reliable Broadcast (BCRB), which builds on BRB to enforce causal message ordering. We present a novel BCRB protocol that decouples causal ordering from the BRB layer, achieving constant-size $\mathcal{O}(1)$ message metadata overhead and $\mathcal{O}(n^2)$ communication word complexity as against $\mathcal{O}(n^3)$ communication word complexity of existing protocols; here $n$ is the number of processes. We present two variants of our protocol: a cryptographic version using a threshold encryption scheme and sequence gating, and its non-cryptographic version. In the cryptographic version, senders broadcast ciphertexts immediately, and decryption shares are piggybacked on out-of-band ACKs, preventing early decryption and front-running. In both versions, causal safety is achieved probabilistically. We evaluate the probability of causal safety violations using a random variable path analysis under independent exponential link delay distributions. We show that both variants satisfy liveness and the probability of weak safety violation is bounded by $\mathcal{O}(f^{-3}\cdot\ln^3 f)$, where $f$ is the upper bound on the number of Byzantine processes, and $f < n/3$ and $f=\mathcal{O}(n)$. Further, for the crypto version, we show that the probability of strong safety violation is bounded by $\mathcal{O}(f^{-1} \cdot \ln^2 f)$. We also show how to modify our two protocols to guarantee 100\% weak safety keeping $\mathcal{O}(1)$ message space overhead but with $\mathcal{O}(n^3)$ messages and $\mathcal{O}(n^3)$ communication word complexity.

cs.DC↗