Local AI Bench is made and published by Minwoo Jung. AppBrain is an independent app data site and isn't affiliated with Minwoo Jung. The app name, icon, screenshots and description belong to Minwoo Jung and are shown as published on the App Store.
AppBrain's verdict
- Last updated
- October 5, 2026
Rankings
App Store top chartsApp Store Rankings for Local AI Bench
Competitors
Similar apps and more from Minwoo JungMore from Minwoo Jung
Releases
Updates seen on the App Store- Version
- 1.1.4
- Launched
- June 2026
No changelog data
User feedback
Ratings and reviews on the App StoreComments on Local AI Bench for iOS
We don't have enough comments to show example comments. Please check back later.
Technology
Found in the app by AppBrain- Price
- Free
- App size
- 31.7 MB
- Content rating
- Everyone
Technologies used by Local AI Bench
About the app and developer
About Local AI Bench
Local AI Bench is a productivity app developed by Minwoo Jung.
User Ratings
The app has no ratings yet.
App Information
Local AI Bench is freely available from the App Store. The app size is 31.71 MB. The latest version available is 1.1.4. The last update was on October 5, 2026.
Technical Requirements
The app has a content rating of Everyone. The app has been available on the App Store since June 2026.
Developer information for Minwoo Jung
Address:
Frequently asked questions about Local AI Bench
Is Local AI Bench free?
Yes. Local AI Bench is free on the App Store.
Is Local AI Bench still available?
Yes. Local AI Bench is on the App Store, and the last update we saw was on October 5, 2026.
How large is Local AI Bench?
Local AI Bench is 31.71 MB.
Is Local AI Bench suitable for children?
App Store rates the content of Local AI Bench as suitable for everyone.
Who made Local AI Bench?
Local AI Bench was developed by Minwoo Jung. It is listed in the productivity category on the App Store.
Store listing
By Minwoo Jung, from the App StoreDescription by Minwoo Jung Written by the developer, not by AppBrain. Click to read.
■ 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.