UlukaDev author hub
bitnet ternary moe gguf 🧮 A 1GB Mixture of Experts model designed to run efficiently on an everyday laptop CPU, with no GPU needed. A single 1.58 bit BitNet base model with two lightweight LoRA expert adapters multiplication and Roman numerals that are dynamically activated at …
Models
2
Downloads
2,231
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.