# Bench360: Benchmarking Local LLM Inference from 360 Degrees

arXiv: https://arxiv.org/abs/2511.16682 · HTML: https://mlsanity.com/paper/2511.16682/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization](https://mlsanity.com/paper/2505.06371/) (2025)
- [LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators](https://mlsanity.com/paper/2411.00136/) (2024)
- [NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist](https://mlsanity.com/paper/2305.08566/) (2023)
- [Part-time Power Measurements: nvidia-smi's Lack of Attention](https://mlsanity.com/paper/2312.02741/) (2023)
- [SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark](https://mlsanity.com/paper/2411.05521/) (2024)
- [Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries](https://mlsanity.com/paper/2402.08349/) (2024)
- [LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind](https://mlsanity.com/paper/2508.15601/) (2025)
- [Inference Optimization of Foundation Models on AI Accelerators](https://mlsanity.com/paper/2407.09111/) (2024)

## Built on by (most cited first, 4 of 4)

- [Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces](https://mlsanity.com/paper/2606.06941/) (2026)
- [SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops](https://mlsanity.com/paper/2609.19169/) (2026)
- [The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models](https://mlsanity.com/paper/2609.31341/) (2026)
- [Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing](https://mlsanity.com/paper/2610.09778/) (2026)

## Abstract (arXiv)

Running LLMs locally has become increasingly common, but users face a complex design space across models, quantization levels, inference engines, and serving scenarios. Existing inference benchmarks are fragmented and focus on isolated goals, offering little guidance for practical deployments. We present Bench360, a framework for evaluating local LLM inference across tasks, usage patterns, and system metrics in one place. Bench360 supports custom tasks, integrates multiple inference engines and quantization formats, and reports both task quality and system behavior (latency, throughput, energy, startup time). We demonstrate it on four NLP tasks across three GPUs and four engines, showing how design choices shape efficiency and output quality. Results confirm that tradeoffs are substantial and configuration choices depend on specific workloads and constraints. There is no universal best option, underscoring the need for comprehensive, deployment-oriented benchmarks.