Top AI Calorie Tracker GitHub 2026
Single-HTML monitoring dashboard for llama.cpp — per-slot sampling, plain-language tuning hints, router-mode aware, with built-in chat. Zero deps.
Ollama server running inside Android - complete offline AI inference with Go backend, WebView UI, and JNI bridge. No internet, no tracking, full privacy.
Cross-platform distributed LLM inference — pool Mac, Windows, Linux, NVIDIA, AMD, and Apple Silicon into one AI cluster. Run large local models across mixed hardware without buying the same device twice.
Fine-tune your own LLM on an AMD Radeon GPU — the easy, tested way. QLoRA via ROCm on Windows/WSL2 & Linux, a worked Gemma-4 example, a reusable live training dashboard, and a smoke test that proves the loss falls.
🌐 Run GGUF models directly in your web browser using JavaScript and WebAssembly for a seamless and flexible AI experience.
BRAINY.AI is a premium, fully offline AI chat application that runs Large Language Models (LLMs) directly on your Android device — no internet connection required. Powered by the llama.cpp engine, it supports GGUF model formats with GPU hardware acceleration and forced runtime overrides.
The Ark Project: Selecting the perfect AI model to reboot civilization from a 64GB USB drive. Comprehensive analysis of open-source LLMs under extreme constraints, with final recommendation: Meta Llama 3.1 70B Instruct (Q6_K GGUF). Includes interactive tools, detailed comparisons, and complete implementation guide for offline deployment.
Free up iCloud space — keep every photo on your own Mac. Private AI photo search from your phone. 100% local AI, free.
Real, reproducible LLM inference benchmarks on the NVIDIA DGX Spark — parallel agent sessions, tok/s and latency under load, with an interactive dashboard and one-command recipes
MCP server and WebUI for TranslateGemma running via llama.cpp
Run private local LLMs and an Ollama/OpenAI-compatible API server on Android
little single file fronted for llama.cpp/examples/server created with vue-taildwincss and flask
A python application for running local, GGUF-based LLMs text generation, document-grounded retrieval, semantic search, prompt engineering, multi-modal workflows, and web context ingestion.
Real-time, zero-dependency dashboard for a llama-swap server — live model, token throughput, context-window usage, GPU/system stats, and streaming logs in a single page.
Self-hosted AI studio for local LLMs, image generation, video, music, and TTS with a unified GPU dashboard.
Local document redaction, measured. A stock quantized Gemma E2B plus deterministic rails remove identifying spans on your own machine; nothing leaves it. Ships with the whole benchmark — 118 real documents, every miss named, and one offline command that recomputes every published number.
Add a description, image, and links to the llama-cpp topic page so that developers can more easily learn about it.
To associate your repository with the llama-cpp topic, visit your repo's landing page and select "manage topics."