Trending Local LLMs repos

Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, or just a CPU.

The open-source AI voice studio. Clone, dictate, create.

使用稠密算力卡对稀疏大显存主机进行加速，主机包括 AI Max+ 395、M3 512G、DGX Spark 等。

Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

On-device ComfyUI style node graph for image/video diffusion models on Android. Local SD1.5, SDXL, Flux, Z-image, Anima, Qwen Image 2.1, Krea 2, text to image, img2img, inpainting, outpainting, controlnet, LoRA, IPAdapter and WAN 2.2 5B video generation/ video motion transfer on the Qualcomm Hexagon NPU. Fully offline, no server, no account.

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X exclusive model access! 😉 - https://x.com/fluidvoiceapp

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

A self-contained native runtime and model format for local AI video generation.

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

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

Open-source, bring-your-own-key (BYOK) multi-model AI chat client for iOS, Android and the web. One LLM client for OpenAI, Anthropic, Google Gemini, OpenRouter, DeepSeek and ten more providers, plus any OpenAI-, Anthropic- or Gemini-compatible endpoint — Ollama, LM Studio, llama.cpp, vLLM. Local-first, self-hostable, no account. AGPL-3.0.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes

Run LLMs with MLX

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

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

An open-source, privacy-first macOS text action popup for running custom scripts, AI-powered actions, and extensible workflows on selected text.

Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台/ Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Matrix e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, GLM, Ollama, SiliconFlow, Moonshot, openclaw / hermes agent, deerflow

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms

Distribute and run LLMs with a single file.

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.

🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

A harness optimized to smaller LLMs

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.

LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.

The Ruby AI framework.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

An AI-powered search engine with a generative UI