AI Chat: Local LLM & GGUF

AI Chat: Local LLM & GGUF

Run GGUF models on your iPhone

0 ratings
Free

Rating summary

Details

Released
November 4, 2026
Updated
November 16, 2026

Features

AI Chat: Local LLM & GGUF screenshot #1 for iPhone
AI Chat: Local LLM & GGUF screenshot #2 for iPhone
AI Chat: Local LLM & GGUF screenshot #3 for iPhone
AI Chat: Local LLM & GGUF screenshot #4 for iPhone
AI Chat: Local LLM & GGUF screenshot #5 for iPhone
AI Chat: Local LLM & GGUF screenshot #6 for iPhone
iphone
iphoneDuo
ipad
🖼️Get Icon
Icons↘︎

About

AI Chat is a local AI chat app that works even without an internet connection. Conversations are processed entirely on your iPhone or iPad. What you type, attach, and receive is never sent to an external server, and it keeps working in Airplane Mode. No cloud AI subscription required. ■ Three simple steps 1. Pick a model that fits your device (or just take the "Recommended" pick) 2. Download it (hundreds of MB to a few GB; Wi-Fi recommended) 3. Start chatting ■ Open models you choose Search Hugging Face for open models in GGUF format (Gemma, Qwen, and more), download them in the app, and run them on your device. Each model is labeled "Runs", "Tight on memory", or "Won't run" for your device. ■ Supported Models (as of v1.0.25) Tested models with tuned settings such as Temperature. Just pick one. - Recommended: Google Gemma 4 (E2B / E4B), Alibaba Qwen3.5 4B / 0.8B - Also supported: Nemotron 3.5 Bolt E4B, Phi-4 mini, Granite 4.2 3B, Bonsai 8B / Ternary Bonsai 2, LFM3 Omni 2B / LFM2.5, Agents-A1 4B, Spark-X2.6, Ministral 3 3B, SmolLM3 3B, MiniCPM5 2B, K2-Horizon, PLaMo 3 Translate, and more You can also try any GGUF that isn't on the list. ■ Photos, audio, and video With Gemma 4 E2B / E4B, Nemotron 3.5 Bolt E4B, and LFM3 Omni 2B, attach photos or audio, or paste a copied image into the input field, and ask about them. For video, the audio is used, and LFM3 Omni 2B also reads the frames. ■ Draw images from text Pick Z-Image Turbo (Alibaba Tongyi Lab) or FLUX.2 klein 4B (Black Forest Labs) to draw an image from what you write (8GB of memory or more). Use "Edit the last image" to refine it or "Draw another version" to redraw it. Images stay in the conversation and can be saved to Photos. ■ Make English natural The "Make English Natural" skill rewrites English papers and text into natural English without changing the meaning, numbers, or citation markers. It also works with PDF and text attachments (Gemma 4 E4B / Nemotron 3.5 Bolt E4B, devices with 12GB of memory). ■ Fine-tune responses - System prompt for personality and tone - Temperature from 0.0 (precise) to 2.0 (creative) - Context size from 2K to 32K (up to 64K with 12GB of memory) - Long-context priority or conversation priority ■ Speed-up methods (experimental) Run a small look-ahead model with the main model: MTP, DFlash, or Speculative Decoding. All are off by default, and some combinations can be slower. ■ Designed for privacy - History and attachments are stored encrypted on your device and included in your iPhone backup - Before connecting to Hugging Face or your own server, the app shows what is sent and where, and asks for your permission - No account or sign-in - No ads, no tracking ■ Turn your iPhone into an AI server Server Mode runs your iPhone or iPad as an OpenAI-compatible API server. Other devices on the same network can use the loaded model. API key authentication is available. ■ Connect to your own server (advanced) Connect over your home network or a VPN such as Tailscale to an OpenAI-compatible server you run (such as llama-server) to use models too large for the device. Only Tailscale, private IP, and .local hosts are allowed, so conversations never go to a public server by mistake. ■ Main features - Streaming replies with Markdown and code blocks - History with search, pinning, renaming, and Markdown export - Attach text files and PDFs; long documents are trimmed only when they don't fit, and the app tells you ■ Requirements The models you can use depend on your device's memory. - 12GB: 8B–9B class models and the 1.75-bit 27B - 8GB (iPhone 15 Pro and later): most supported models - 6GB: models up to about 2.5GB, such as Gemma 4 E2B - 3–4GB: 1B–2B class models such as Qwen3.5 0.8B and LFM2.5 1.2B JP Downloading models needs several GB of storage and an internet connection (only for the download). AI replies can contain mistakes or outdated information; check primary sources for anything important.
Show more
+1

What's New in AI Chat

1.0.25

November 16, 2026

- New skill: Make English Natural. It rewrites English papers and text into natural English without changing the meaning or numbers (Gemma 4 E4B / Nemotron 3.5 Bolt E4B, devices with 12GB of memory). - You can now paste a copied image into the input field to attach it. - For the image generation models (Z-Image Turbo / FLUX.2 klein 4B), you can now choose other quantizations. - The AI model screens in Settings have been reorganized. - Other minor display adjustments and bug fixes.

More