# Local AI Bench

> 오프라인 온디바이스 AI 벤치마크

Canonical page: [https://chrome-stats.com/d/id6780884116](https://chrome-stats.com/d/id6780884116)

## Overview

- **ID:** `id6780884116`
- **Platform:** Apple
- **Type:** Apple app
- **Status:** Available
- **Publisher:** Minwoo Jung
- **Category:** Productivity
- **Version:** 1.1.3
- **Last updated:** 2026-09-12
- **First published:** 2026-06-16
- **Size:** 31 MB
- **Data as of:** 2026-09-22
- **Store listing:** [Apple App Store](https://apps.apple.com/us/app/local-ai-bench/id6780884116)
- **Privacy policy:** [https://jmwfdisk.github.io/LocalAIBench-catalog/privacy.html](https://jmwfdisk.github.io/LocalAIBench-catalog/privacy.html)

## Description

LocalAI Bench is an on-device benchmark app that runs AI models directly on your iPhone and measures their performance and capabilities. All inference happens inside your device — your conversations and personal data never leave it.

■ On-Device Execution
- Download open AI models (Llama, Qwen, Gemma, Phi, and more) and run them right on your device
- Works fully offline once a model is downloaded

■ Real-Time Performance Metrics
- Generation speed (tok/s), time-to-first-token (TTFT), peak memory (RAM), and thermal state — displayed live while you chat
- Automated benchmark with a standard methodology: repeated measurements of text generation, prompt processing, translation, coding, and math speed

■ Capability Evaluation
- Auto-graded tasks: math, coding, multilingual translation (Korean↔English/Japanese/Chinese), summarization, reasoning, and vision
- Compare capability, speed, and memory at a glance (choose 2-axis, composite, or efficiency scoring)

■ Vision & Speech Models
- Vision: attach photos or recognize objects through the live camera
- Speech: compare Whisper (tiny/base/small) transcription speed (RTF)

■ Compare & Manage Models
- A/B head-to-head between two models, stress tests (thermal throttling curve)
- Search models by capability (vision, coding, reasoning) or vendor and add them, with automatic iOS compatibility checks

■ Web Search (optional)
- When enabled, fetches Wikipedia references for the model — ask about recent events
- Inference stays 100% on-device; automatically skipped when offline

Pure on-device AI — no cloud APIs, no fees, no subscriptions. Runnable models depend on your device's performance; larger models are recommended for devices with more memory.

## Rankings

- #1,016,233 — Overall

## Similar extensions and apps

- [GenBench](https://chrome-stats.com/d/id6775272272)
- [AIBench - Test Speed](https://chrome-stats.com/d/id6741204584)
- [DeviceAI](https://chrome-stats.com/d/id6760162343)
- [Token : Local AI Studio](https://chrome-stats.com/d/id6774354746)
- [Arbor AI: On-Device AI Models](https://chrome-stats.com/d/id6755762723)
- [Geekbench AI](https://chrome-stats.com/d/id1563487010) — 4.20 / 5
- [EdgeAI: Local AI Gallery](https://chrome-stats.com/d/id6766524869) — 5.00 / 5
- [Local AI Chat - Local LLM](https://chrome-stats.com/d/id6762094415) — 3.90 / 5
- [Offline AI - Private Chat](https://chrome-stats.com/d/id6760442643) — 4.10 / 5
- [FIL AI](https://chrome-stats.com/d/id6765593874)
- [InferrLM](https://chrome-stats.com/d/id6754396856) — 5.00 / 5
- [Local AI Chat - pocket](https://chrome-stats.com/d/id6476791661) — 4.40 / 5

---

Source: [Chrome-Stats](https://chrome-stats.com/d/id6780884116)