270M (dense)
Gemma License
Specialized Gemma 3 270M fine-tuned for unified chat and function calling; translates natural language into structured API calls while maintaining conversational ability; achieves 85% accuracy on Mobile Actions benchmark after fine-tuning (vs 58% baseline); designed for edge deployment on mobile phones and devices like NVIDIA Jetson Nano; runs fully offline for privacy; acts as intelligent traffic controller handling simple commands locally while routing complex tasks to larger models; uses Gemma's 256k vocabulary for efficient JSON tokenization; supports multi-turn logic and can decompose complex commands into specific function calls; built for customization with fine-tuning recipes; ecosystem support across Hugging Face Transformers, Unsloth, Keras, NVIDIA NeMo, LiteRT-LM, vLLM, MLX, Llama.cpp, Ollama, Vertex AI; enables private on-device agents that execute API actions.