Aatricks/llmedge
Android native AI inference library, bringing gguf models and stable-diffusion inference on android devices, powered by llama.cpp and stable-diffusion.cpp
Integrates **Whisper.cpp** and **Bark.cpp** for speech inference, with optional GPU acceleration via OpenCL/Vulkan backends; provides native KV-cache optimization and streaming text generation via JNI bindings. Supports multimodal workflows including on-device RAG with PDF indexing, vision models (LLaVA-style), Stable Diffusion with LoRA, and video generation (Wan 2.1), all coordinated through the instance-based `LLMEdge` facade for explicit resource management.
Stars
37
Forks
4
Language
Kotlin
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Aatricks/llmedge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
langbot-app/LangBot
Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台. 提供 Agent、知识库编排、插件系统 /...
open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
cactus-compute/cactus
Low-latency AI engine for mobile devices & wearables
rudrankriyam/Foundation-Models-Framework-Example
Example apps for Foundation Models Framework in iOS 26 and macOS 26
sigoden/aichat
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with...