Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2606.12154

The Brain That Goes Quiet: Serving a Large Model's Knowledge at 131 Tokens per Second on an 8 GB Laptop by Removing the Large Model from the Runtime Path

Myeong Jun Jo
View original source ↗Read source document ↗Export metadata ↓

Abstract

In earlier work I showed that a 35B-class Mixture-of-Experts model can be loaded and executed on a consumer laptop with 8 GB of GPU memory. That result solved a placement problem and immediately exposed a different one: even correctly placed, the large model needed roughly four seconds to answer, because it was still being invoked at every query. This paper documents what happened when I stopped invoking it. During an offline phase, the large model reads source documents and writes verified answer entries into a structured knowledge store; at runtime, only a lightweight router, a deterministic renderer, and a 1B-class model are active. On the same 8 GB laptop, end-to-end response time fell from approximately 4,465 ms to 518 ms, effective end-to-end throughput rose from 15.7 to 131 tokens per second, and the small model's streaming decode rate held at 226-237 tokens per second with a time-to-first-token of 29-62 ms. The bottleneck is structural: three different large models (Qwen, Gemma, and GLM class) all showed the same multi-second runtime cost, and all three produced usable knowledge stores offline. On a 563-entry store built from seventeen real documents, keyword routing collapsed to 1.5% top-1 accuracy while BM25-based routing reached 92.8% (99.4% top-3), and a confidence gate raised effective top-1 to 98.0% by escalating 12.3% of queries. Exact-match fidelity of the small model ranged from 9/9 to 0/9 across envelope formats carrying identical content. A 16-case verification gate blocked all ten corrupted entries while admitting all six supported ones.

Explore related subjects

cs.PF

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Myeong Jun Jo. 2026-06-10. The Brain That Goes Quiet: Serving a Large Model's Knowledge at 131 Tokens per Second on an 8 GB Laptop by Removing the Large Model from the Runtime Path. https://arxiv.org/abs/2606.12154

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

KEEP EXPLORING

Related papers

arXiv2026

Performance Analysis of Low-Order, GPU-accelerated Finite Element Kernels using Kokkos

We study performance portability for low-order, matrix-free finite element kernels, using the example of a vectorial, variable-coefficient PDE operator originating in geophysical models. Written in Kokkos, the kernel is compared on NVIDIA H100, AMD MI250X, AMD MI300A and Intel PVC Max 1550 GPUs. Owing to its low order and to optimizations that reduce the arithmetic, the kernel has a low arithmetic intensity, so that its performance is determined by how the finite element assembly is mapped onto the memory hierarchy. This is a dimension in which the architectures differ even within one vendor family, causing different performance characteristics. We examine how Kokkos' hierarchical parallelism and shared scratch memory, which are used for the shared degrees of freedom of the conforming discretization, behave on each device. Finally, we show how portability gaps can be narrowed with tuning levers such as the size of the thread groups, the balance between occupancy and register use, and the atomic accumulation strategy at the end of the kernel.

cs.PF↗
arXiv2026

Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving

Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend. While in practice, many queries do not require the capabilities of the largest available model, and routinely directing such queries to a high-capability model can introduce unnecessary, considerable computation and energy consumption. In this paper, we investigate whether adaptive routing across a heterogeneous pool of LLMs can reduce this energy burden without substantially compromising task performance. We design a language-model-based router that reads in each query and selects an answer model from a fixed candidate pool. The candidate models are first profiled through an offline tournament that records their correctness, latency, power, and GPU energy for each query. Using these measurements, the router is trained through supervised fine-tuning followed by group relative policy optimization (GRPO) with the tailored paradigms. Results demonstrate that learned routing can selectively allocate expensive model capacity based on query context and improve the accuracy-energy tradeoff in multi-LLM serving. Across seven benchmark tasks, we also observe a sharp accuracy-energy phase transition among routers, providing practical insights into improving energy efficiency while maintaining LLM performance.

cs.PF↗
arXiv2026

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipelines, agent frameworks, and multi-turn conversations. Modern inference runtimes such as vLLM and TensorRT-LLM provide mechanisms for reusing previously computed KV-cache state across requests, yet it remains unclear when prefix reuse materially improves serving performance on contemporary accelerators and when its benefits are limited by scheduling, cache granularity, concurrency, or memory pressure. This paper presents PrefixBench-H100, a reproducible benchmark and measurement framework for characterizing prefix reuse on a single NVIDIA H100. PrefixBench-H100 combines controlled synthetic traces with chat-style and retrieval-style workloads, and evaluates two widely used LLM serving runtimes under matched workload conditions. The benchmark varies shared-prefix length, suffix diversity, request arrival pattern, concurrency, output length, and cache configuration, while collecting time-to-first-token, inter-token latency, end-to-end latency, throughput, cache-hit statistics, GPU memory usage, and selected profiling traces. The goal of PrefixBench-H100 is not to introduce a new caching algorithm, but to expose the practical operating envelope of prefix reuse for H100-class LLM serving. The study identifies the regime where prefix reuse provides substantial first-token latency reductions and the regime where cache pressure erodes them, while showing that cache effectiveness itself is largely insensitive to concurrency and output length; the cross-runtime differences that remain arise above the cache, in the scheduling layer.

cs.PF↗