Local LLM: On-Device – On-device AI chat that feels closer to Gemini
None of the on-device LLMs I tried on iPhone felt close to Gemini, ChatGPT, or Claude, so I built one that runs locally and aims for that kind of UX. The local LLM runs Qwen, Gemma, and other small models on your iPhone without an account. Chats stay on device. Download a model f
In plain words
Local LLM: On-Device is an iPhone app that runs artificial intelligence chat models directly on the phone without requiring an account or internet connection. It offers a user experience similar to Gemini, ChatGPT, and Claude by running smaller models like Qwen and Gemma locally. Users download a model first, then can chat offline with their conversations remaining private on their device. The app optionally includes web search via DuckDuckGo when enabled and requires iPhone 14 or newer.
written from the facts on this page · September 2026
From the sources
Using TestFlight is a great way to help developers test beta versions of their apps.
Help developers test beta versions of their apps and App Clips using the TestFlight app. Download TestFlight on the App Store for iPhone, iPad, Mac, Apple TV, Apple Vision Pro , Watch, and iMessage. Local LLM runs large language models entirely on your iPhone — no account, no cloud chat history. Download curated MLX models from the in-app catalog, chat with text or voice, attach photos and files, and try vision models when your device has enough memory. Live mode adds hands-free voice conversation with on-device speech recognition and read-aloud replies. This beta is for early feedback on performance, model downloads, chat quality, and voice features. Expect rough edges:…from testflight.apple.com
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, September 2026
the whole month →
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API. - carloslfu/slotstream
Dev tools · 5d ago · github.com
NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs. - NPC-Forge/docs/development.md at main · gioblu/NPC-Forge
AI · 2d ago · github.com
Weedout is a Safari extension that filters out videos YouTube labels as “Made with AI”.
AI · 4d ago · masteranza.github.io
Find your next hire or your next role from Hacker News monthly threads. AI-powered matching between candidates and job postings.
AI · 5d ago · hnmatchmaker.com
I made OwnTime to balance between competing priorities in my life. The idea is based on two main influences: the concept of "roles" from "The 5 Choices" (2015), and my repeated failure to effectively implement time blocking due to the necessary flexibility in my role. The app allows you to define time budgets, which are not much more than a few mutually exclusive countdown timers. The UX is essentially that of a chess clock for an arbitrary number of players with configurable time. The whole point of the app is to kick you out of the running role/priority when its time is up. One…
Life & fun · 5d ago · owntime.app