HAPIE Desktop v1.0 is now live!Get Started
HAPIE - The Next-Gen AI Inference Engine
A premium, local-first platform for lightning-fast AI inference. Hardware-aware optimization that dynamically scales across your local CPU and GPU for maximum performance.
Core Features
Hardware Detection
Automatic CPU, RAM, and GPU detection for optimal performance.
Dynamic Execution
Supports NVIDIA CUDA, AMD, Intel GPUs, and CPU-only gracefully.
Model Management
Pull models from HuggingFace, local GGUF, or use cloud API models.
Chat Modes
Single-model chat for minimal resources or full Comparison Mode.
Multimodal (Soon)
Image generation, Text-to-Speech (TTS), and Speech-to-Text (STT) coming soon.
Docker Ready
Easily run with a single setup script and docker-compose.