Compute Engine M4N Machine Series for Network-Intensive Workloads Now GA
The M4N machine series in Google Cloud Compute Engine is now generally available, providing network- and memory-optimized instances. Powered by 5th generation Intel Xeon Scalable processors, these instances are purpose-built for high-performance vector databases, retrieval-augmented generation (RAG) data layers, and real-time semantic search. They offer up to 400 Gbps of network bandwidth and leading block storage performance with Hyperdisk Extreme, scaling to 25 GiB/s and 1M IOPS. M4N instances range from 16 to 224 vCPUs and up to 5,952 GB of DDR5 memory, making them suitable for demanding I/O workloads.
Features (1) ›
- Compute Engine Generally available
Generally available : The network- and memory-optimized M4N machine series is generally available. Powered by 5th generation Intel Xeon Scalable processors (Emerald Rapids), M4N instances are purpose-built for network and block storage-intensive workloads such as: High-performance vector databases Retrieval-augmented generation (RAG) data layers Massive in-memory context caching Real-time semantic search The M4N machine series delivers the highest I/O performance available in Compute Engine, supporting up to 400 Gbps of network bandwidth. M4N also offers leading block storage performance with
https://docs.cloud.google.com/release-notes#August_21_2026
Related releases
- Managed Service for Apache Spark Updates Image Versions with Iceberg 1.10 and OpenLineage 1.49 Google Cloud release notes ·
- Google Cloud Backup and DR adds selective disk backup for Compute Engine VMs Google Cloud release notes ·
- Google Cloud Migration Center Introduces AI-Powered Quick Assessments Google Cloud Blog ·
- Compute Engine Image Builder enters allowlist-only Preview Google Cloud release notes ·
- 10 Questions for Scaling AI Prototypes to Production on Google Cloud Google Cloud Blog ·
- Batch Deprecates Debian 11 OS Image Family Google Cloud release notes ·