Replaces cloud-based AI APIs with a private, local server that requires no GPU. Optimized for CPU-based inference of Llama, Mistral, and Whisper models using quantized weights.
Tech Stack
RustAI, ML & Data
Why edgen?
• No GPU required
• Cross-platform support
• Private by design
Limitations
• Slower than GPU inference
• Limited to quantized models
• Manual model management
2/27/2026
Last Update
20
Forks
25
Issues
Apache-2.0
License
Financial Leak Detected
Stop the "SaaS Tax"
Your team could be burning cash. Switching to edgen instantly boosts your runway.
