Browse AI Projects by Category

Local Models / Ollama

Browse AI open-source projects in Local Models / Ollama from the current public snapshot, including licenses, deployment, use cases, limitations, and verified sources.

open-webui/open-webui — A self-hostable web interface for managing and interacting with LLM runners and AI features. It is designed to operate entirely offline and supports various model providers alongside built-in retrieval augmented generat…
ollama/ollama — Ollama simplifies downloading and running open large language models on local hardware. It provides a command-line interface and a REST API for local model inference, text prompt processing, and text response generation.
vllm-project/vllm — vLLM is a high-throughput, memory-efficient inference and serving engine for large language models. It provides an OpenAI-compatible API server and uses PagedAttention to manage attention key and value memory efficientl…
ggml-org/llama.cpp — llama.cpp is a dependency-light C/C++ implementation for running LLM inference across diverse hardware. It provides tools for quantization, benchmarking, and serving, requiring models in the GGUF format.
lyogavin/airllm — AirLLM enables 70B-parameter Hugging Face language models to run on a single 4GB GPU by loading only one model layer at a time. This memory reduction is achieved without quantization, distillation, or pruning, but infer…
rasbt/LLMs-from-scratch — A step-by-step educational tutorial for implementing a small-but-functional GPT-like large language model from scratch using PyTorch and Python. It is designed for learning the internal mechanics of LLMs, including data…
jamiepine/voicebox — A local-first voice I/O stack that combines dictation, text-to-speech, voice cloning, and agent voice output. It is built with Tauri (Rust) and routes audio processing through local models such as Whisper and Kokoro.
ChatGPTNextWeb/NextChat — A lightweight, cross-platform chat application that connects to multiple LLM providers and stores user data locally in the browser. It requires an external paid API key to function.
unslothai/unsloth — A library and local web UI for running and fine-tuning language, audio, embedding, and vision models on your own hardware, designed to reduce speed and VRAM requirements. It provides automated installation, document-bas…
OpenBMB/VoxCPM — VoxCPM is a tokenizer-free text-to-speech model supporting 30 languages and 48kHz audio output. It enables voice creation from text descriptions and reference-audio voice cloning, runnable locally via CLI, library, or w…
jingyaogong/minimind — An open-source educational project that enables individuals to train and understand a 64M-parameter LLM from scratch in approximately 2 hours using native PyTorch. It covers the complete model training lifecycle and pro…
tinyhumansai/openhuman — OpenHuman is a local-first personal AI application for persistent memory, durable multi-agent workflows, and research across personal data and the web. It combines local memory storage with optional external services, r…
ggml-org/whisper.cpp — A plain C/C++ automatic speech recognition implementation that performs dependency-free inference using OpenAI Whisper models converted to ggml format. It provides a C-style API, CLI, and an HTTP server example for inte…
agentscope-ai/QwenPaw — QwenPaw is a personal AI assistant designed for private deployment across user-owned machines or the cloud, featuring persistent three-layer memory, multi-agent execution, and multi-channel connectivity. It supports loc…
AlexsJones/llmfit — This project helps determine which large language models will run adequately on a specific computer by evaluating system RAM, CPU, and GPU resources. It scores models on memory fit, estimated speed, quality, and context…
Zackriya-Solutions/meetily — Meetily is a desktop application that captures, transcribes, and summarizes meeting audio. It processes audio on the local machine using local models, with optional cloud-based language models for generating summaries.
CorentinJ/Real-Time-Voice-Cloning — A toolbox and CLI for cloning a voice from a few seconds of audio and synthesizing arbitrary speech in real-time using the SV2TTS deep learning framework. It is a research implementation intended for local execution and…
cactus-compute/needle — Needle is a single 8-29 MB binary foundation model that runs capable inference on tiny devices such as phones, wearables, robots and microcontrollers. It combines tool calls, structured extraction, embeddings and speech…
janhq/jan — Jan is a desktop application for downloading and running large language models locally or connecting to cloud-based models. It provides a graphical interface and a local API server for text-based model interaction witho…
chatboxai/chatbox — Chatbox is a cross-platform desktop, web, and mobile AI copilot that unifies access to multiple LLM providers under a single interface. It stores user data locally on the device while requiring users to connect their ow…
HandsOnLLM/Hands-On-Large-Language-Models — A tutorial repository providing runnable Jupyter notebooks that accompany the book 'Hands-On Large Language Models', spanning introductory LLM concepts to advanced topics like semantic search, multimodal models, and fin…
oobabooga/textgen — A desktop application and local API server for running large language models privately on your own hardware. It supports text generation, vision input, tool calling, image generation, and exposes OpenAI/Anthropic-compat…
jundot/omlx — A local LLM inference server for Apple Silicon that addresses the tradeoff between convenience and control by offering continuous batching, persistent tiered KV caching across restarts, and multi-model management throug…
SYSTRAN/faster-whisper — faster-whisper delivers up to 4x faster Whisper transcription with lower memory usage using CTranslate2. It supports int8 quantization, voice activity detection, and batched inference on both CPU and CUDA GPUs.
microsoft/BitNet — BitNet is a Microsoft open-source framework of optimized kernels for fast, lossless inference of 1.58-bit (ternary) LLMs on CPU and GPU. It builds on the llama.cpp framework so these models can run on local devices with…
mozilla-ai/llamafile — Llamafile packages open large language models into a single-file executable that runs locally across most operating systems and CPU architectures without installation. It combines llama.cpp with Cosmopolitan Libc to sim…
babysor/MockingBird — A voice cloning and speech synthesis toolkit supporting Mandarin Chinese and English, capable of generating speech from a 5-second audio sample. It offers self-hosted execution and training workflows but requires advanc…
AAswordman/Operit — Operit is an Android AI assistant with local model support, an embedded Ubuntu environment, tool extensions and device automation. Cloud models are optional and user configured.
Fosowl/agenticSeek — fosowl/agenticseek is a local AI assistant that can autonomously browse the web, write and run code, and plan multi-step tasks on a user's own hardware. It is positioned as a private, local alternative to cloud-based au…
mckaywrigley/chatbot-ui — An open-source AI chat application that connects to any AI model and can be deployed locally or in the cloud. It requires terminal usage, a Supabase backend, and an AI model provider to operate.
Osmantic/ODS — ODS is a one-command installer that detects your hardware and auto-configures a full local AI stack covering chat, LLM inference, voice, image generation, RAG, and workflow automation. After installation, an Open WebUI…
GeeeekExplorer/nano-vllm — nano-vllm is a lightweight Python library that reimplements vLLM's offline LLM inference in roughly 1,200 lines of code. It provides a code-based interface for running locally downloaded Hugging Face models with optimiz…
Open-LLM-VTuber/Open-LLM-VTuber — A voice-interactive AI companion application that combines real-time speech, visual perception, and Live2D avatars. It supports local execution and extensive LLM, ASR, and TTS backend integrations, with data boundary an…
lightningpixel/modly — modly is an open source desktop application that generates 3D models from images using AI models running entirely on the user's own GPU. It supports workflows that turn photos into 3D meshes locally, without cloud-based…
AI4Finance-Foundation/FinGPT — FinGPT provides open-source financial large language models and benchmarks that can be fine-tuned at low cost. It addresses the prohibitive expense of training financial models from scratch and the inaccessibility of in…
mlc-ai/mlc-llm — mlc-llm is a machine learning compilation and inference solution for developing, optimizing, and deploying large language models natively across heterogeneous hardware and software platforms. It provides a unified deplo…
elizaOS/eliza — An agent operating system that unifies chat, voice, personal assistant tasks, browser automation, and cryptocurrency wallet actions across multiple platforms. It is designed to run the agent, user data, and models local…
QwenLM/Qwen — Qwen is an official open-source release of large language models providing pretrained chat models for conversational and general natural language processing tasks. It is available in multiple sizes and quantized version…
rowboatlabs/rowboat — A desktop AI coworker that maintains long-lived knowledge by indexing email, meetings, and Slack conversations into a backlinked knowledge graph, acting through built-in email, browser, and background agent surfaces. It…
FareedKhan-dev/kimi-k3-in-c — kimi-k3-in-c runs inference on a 2.78-trillion parameter mixture-of-experts language model using as little as 8.24 GB of RAM on a single CPU by streaming non-resident experts from disk. It is written in portable C99 wit…

Search

Browse AI Projects by Category