TokForge Local AI Offline Chat

Defcon-One

About this app

TokForge 1.0 is here. Full AI models run directly on your phone. No cloud, no account, no subscription. Your conversations never leave your device.

Chat and roleplay. Create characters or import cards from chub.ai and TavernAI (PNG/JSON). Personas, lorebooks, alternate greetings, and group chats where every character can speak with its own voice.

Generate images on-device. Type a prompt and get a picture without an internet connection. Runs on CPU everywhere, with GPU acceleration on Adreno and NPU acceleration on supported Snapdragon devices.

Talk to it. Kokoro text-to-speech with multiple voices, plus voice cloning: record about a minute of audio and TokForge speaks in that voice. Voice input included.

Ask your documents. Drop in a PDF, DOCX, EPUB, Markdown, CSV, or text file and ask questions about it. Long-term memory and a knowledge graph keep track of what matters across conversations.

Web search, when you want it. Off by default. Turn it on to give the model current information.

Three engines, tuned for your chip. llama.cpp (GGUF) with OpenCL and Vulkan GPU paths, MNN with OpenCL, or connect to your own OpenAI-compatible server. SoC-aware routing picks the fastest path automatically.

Find and benchmark models. A curated catalog of 52 models matched to your device, plus a built-in downloader with Hugging Face search. AutoForge benchmarks every model and backend combo on your hardware and posts to the public leaderboard at leaderboard.tokforge.ai if you choose.

Backup and restore your conversations, characters and settings. Developer API with 270+ local endpoints. Zero analytics, zero telemetry, works in airplane mode. Available in 8 languages.

Community.
Discord: discord.gg/Acv3CBtfVm
Leaderboard: leaderboard.tokforge.ai
Web: tokforge.ai

iPhone and iPad: TokForge is available as a public beta on TestFlight.

Ratings and reviews

glad to finally have a local only ai, very customizable. Works great on my fold8. Would recommend to anyone who wants to use AI but would prefer not to trust the cloud and for profit companies with their data.

Great offline AI app. Easy to use, and all in one. Lots of models for various ram limits. Dev is helpful and seems to care about the user experience. Absolutely one of the best apps of its kind.

slow and forced to talk to a fantasy app. not sure how it's well rated I found it horrible to use.

What’s new

Attached documents: questions about an amount now quote the matching line instead of "not specified"; non-English documents index in seconds; a second attachment no longer gets stuck. AutoForge thread sweeps measure each candidate honestly. Stop now interrupts helper-backed image and audio turns; loads that stall are cut off and cleaned up. Failed replies are kept as diagnostics. Includes the 1.3.2.1 chat fix.