Apps tagged with 'Local LLM'

Private offline on-device local LLM app by Ente, open source code, no accounts or tracking, and works cross-platform on mobile and desktop devices.

Privacy-focused open-source chatbot running locally on consumer CPUs without GPU or internet, supporting multiple customizable large language models and licensing.

Run large language models offline with a built-in chat UI, OpenAI-compatible server, HuggingFace integration, local discovery, private model management.

Dictation app transcribes speech with multiple AI backends, supports local and cloud processing, hotkey activation, auto-paste, and privacy-focused controls.

AI-powered command bar for Windows 10 and 11 centralizes productivity, featuring clipboard privacy, batch image actions, reminders, and advanced AI writing tools.

Access on-device Apple LLM through a local command-line interface on Macs with Apple Silicon, supports function calls, OpenAI-compatible server, no cloud or keys.

Free, open-source voice app that types what you say into any app, answers questions, and writes up your meetings, all on your own computer.

Private, on-device recording and transcription tool with speaker identification, Markdown notes, AI assistant, and customizable triggers. Zero data leaves device.

Kolibri is Aleph Alpha's mixture-of-experts (MoE) reasoning model, with a focus on German and English. The model supports an explicit reasoning mode and tool calling. It is optimized for long-context and inference efficiency.

Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.

Clef is a 27B multimodal model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question in a single forward pass.

A control room for AI memory. Your files and conversations become searchable memory any model you connect can draw on, and you decide what enters, what moves and what leaves. Vaults live on your hardware.

Custom Swift and Metal runtime enabling 26B instruction-tuned model inference in around 2 GB RAM by streaming weights from SSD, optimized for Apple Silicon Macs.

Offline AI companion for Mac and Windows. Your model, memory, and image generation stay on your machine - no account, no subscription, no server to disappear.

Find out which AI models your machine can actually run.

Hundreds of models & providers. One command to find what runs on your hardware.

Warden is a minimalist, simple and beautiful macOS AI chat app, that supports most AI providers: ChatGPT, Anthropic (Claude), xAI (Grok), Google Gemini, Perplexity, Groq, Local LLMs through Ollama, OpenRouter, and almost any OpenAI-compatible APIs.

NameQuick is the app that renames files based on their content, for Mac and Windows. It reads PDFs, scans, images and Office documents, applies your naming template, and files them with review, rules, watch folders and undo.

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.

AI-powered CLI that analyzes your hardware and recommends optimal LLM models you can run locally, with full Ollama integration.

A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software.

SmolChat allows you to download and run popular LLMs on your Android device, locally, without needing an internet connection. Customize the model used for each chat, tune settings like temperature and min-p, and pin your favourite chats on the home-screen with shortcuts.

The offline AI-powered Mac file organizer that automatically sorts, categorizes, and declutters your desktop. It turns a chaotic Downloads folder into clean, named folders in minutes.

Polycode is a native macOS chat client for developers who use more than one AI model. It sends every prompt to each provider you configure, in parallel. A primary model reads every reply and writes one answer.