TinyLlama AI - Optimized for Next.js

TinyLlama model aliases for tokkit.

AI-powered git commit message suggester using Ollama + tinyllama

Download, run, and serve local AI models through a gateway-first CLI with OpenAI- and Ollama-compatible APIs.

Run LLMs locally in Node.js with an OpenAI-compatible API

On-device LLM inference for React Native with Metal (iOS) and Vulkan (Android) GPU acceleration

Hardware accelerated language model chats on browsers

Neuronix GPU Provider Node — earn by contributing compute to the Neuronix network

🍩 Donut Corp — local LLM CLI, API & desktop app powered by Donut Runtime.

Host LLM inference for the Pied Piper network from your terminal and earn credits. Serves models through a local Ollama.

🍩 Local LLM runtime optimized for minimal disk usage — run AI models locally without the bloat.

OpenVINO Generative AI integration for LangChain.js

🍩 Donut Corp Runtime — native PC inference engine, no C++ compilation needed

Offline local AI chat and LLM inference for React Native with streaming token responses and GGUF support.

Structured JSON outputs from LLMs

Zero-config, AI-native web framework with embedded LLMs

On-device ML inference for React Native - Run ONNX and CoreML models locally