🤖 Qwen 2.5-1.5B Android
Quantized versions of Qwen 2.5-1.5B Instruct optimized for Android devices.
📦 Models
- qwen-1.5b-q4.gguf (1.12 GB): High-end Android phones (8GB+ RAM)
- qwen-1.5b-q3.gguf (924 MB): Mid-range Android phones (4GB+ RAM)
Both use GGUF format for fast inference with llama.cpp.
📲 Usage
- Download the model file
- Install a GGUF-compatible app (MNN LLM, ChatterUI, or similar)
- Load the model and run fully local — zero cloud dependency
🔗 Links
