# What's the inference latency for Gemma 4 embeddings?

Source: https://zilliz.com/ai-faq/whats-the-inference-latency-for-gemma-4-embeddings
Author: zilliz

Gemma 4 achieves sub-second embedding generation on modern GPUs, enabling real-time indexing into Zilliz Cloud.
---
**Related Resources**
- [Zilliz Cloud — Managed Vector Database](https://zilliz.com/what-is-zilliz-cloud) — fully managed Milvus
- [What Is a Vector Database?](https://zilliz.com/learn/what-is-vector-database) — background concepts
- [Retrieval-Augmented Generation](https://zilliz.com/learn/Retrieval-Augmented-Generation) — RAG fundamentals
- [Start Free on Zilliz Cloud](https://cloud.zilliz.com/signup) — get started today