Google Developer: Hybrid LLMs: Utilizing Gemini and Gemma for edge AI applications

Author: Google for Developers - Bewertung: 26x - Views:300

Discover how to build efficient edge AI applications with Google tools using Hybrid LLMs. Explore on-device and cloud-based models, leveraging both Gemma and Gemini through sequential, parallel and routing architectures. Optimize queries for performance, privacy, and model capabilities to meet your app needs..



Resources:

Discover Gemma capabilities→ https://goo.gle/try-gemma

Gemma Cookbook → https://goo.gle/gemma-cookbook

Google AI Studio → https://goo.gle/aistudio

Get started with the Gemini API → https://goo.gle/gemini-get-started

MediaPipe samples → https://goo.gle/gemma3-mediapipe-llm

Run Gemma with Ollama → https://goo.gle/gemma3-ollama

Serving Gemma 3 with Ollama on Cloud Run → https://goo.gle/gemma3-cloudrun-ollama

Serving Gemma 3 with vLLM on Cloud Run → https://goo.gle/gemma3-cloudrun-vllm



Subscribe to Google for Developers → https://goo.gle/developers





Speaker: Ian Ballantyne

Products mentioned: Gemma