Midrange all-flash power — 330 PB effective scale, NVMe/RDMA, and NVIDIA DGX SuperPOD ready
The NetApp AFF A70 is a 4U all-flash unified storage system delivering 6.6 PB raw per HA pair, 24-node scale-out to 330 PB effective capacity, NVMe/RDMA support, and full ONTAP data management. Purpose-built for demanding enterprise, AI, and cloud-connected workloads.
Get Pricing — Speak to Our Team
Competitive pricing · Response within 4 hours
The AFF A70 delivers NVMe/FC and NVMe/TCP host connectivity with additional NFS/RDMA support for direct memory-to-storage transfers. 56 × 64Gbps NVMe/FC ports and 24 × 200Gbps Ethernet provide the I/O bandwidth for AI data pipelines, Oracle RAC, and high-throughput analytics that cannot tolerate storage bottlenecks.
The AFF A70 is certified for NVIDIA DGX SuperPOD AI infrastructure deployments — validated to feed NVIDIA DGX H100 GPU clusters at the throughput required for large language model training and GPU-scale inferencing. Alongside ONTAP's NFS capabilities, it provides the storage fabric for the world's most demanding AI workloads.
ONTAP provides intelligent inline deduplication, compression, compaction, QoS, SnapMirror synchronous/asynchronous replication, MetroCluster active-active mirroring, and FabricPool cloud tiering. A single AFF A70 HA pair simultaneously serves NVMe block, NFS file, SMB/CIFS, and S3 object workloads under one management interface.
ONTAP Autonomous Ransomware Protection (ARP) uses AI/ML to detect ransomware in real time with 99%+ accuracy, creating automatic immutable snapshot recovery points on detection. NetApp's Ransomware Recovery Guarantee provides a formal commitment to full data restoration — the industry's most comprehensive ransomware assurance.
NetApp BlueXP provides a single control plane for managing AFF A70 data across on-premises, AWS, Azure, and GCP deployments. FabricPool tiering, Cloud Volumes ONTAP, and Azure NetApp Files extend ONTAP data services across the hybrid cloud — providing consistent data management from edge to cloud.
Scale from a single AFF A70 HA pair to 24 nodes (12 HA pairs) without service interruption, growing NAS effective capacity to 330 PB. Non-disruptive controller upgrades protect the infrastructure investment as performance and capacity requirements evolve over the platform lifecycle.
The NetApp AFF A70 is the midrange platform in NetApp's all-flash AFF A-Series portfolio — a 4U unified storage system engineered for organisations requiring high performance, massive scale, and comprehensive data services across block, file, and object workloads.
At the heart of the AFF A70 is ONTAP, NetApp's intelligent storage operating system. ONTAP delivers always-on inline deduplication and compression, achieving typical 5:1 or greater storage efficiency ratios. SnapMirror provides synchronous and asynchronous replication for disaster recovery, while MetroCluster delivers continuous synchronous mirroring across two active data centres for zero RPO, zero RTO business continuity.
The AFF A70 is certified for NVIDIA DGX SuperPOD — validating its performance as the storage foundation for GPU-scale AI training infrastructure. NFS/RDMA support delivers direct memory access for AI data pipelines, reducing CPU overhead and maximising GPU utilisation during training. This positions the AFF A70 as the natural storage choice for organisations building AI Centres of Excellence.
Security is comprehensive: AI/ML-based Autonomous Ransomware Protection with real-time detection and immutable snapshots, NetApp's Ransomware Recovery Guarantee, AES-256 encryption at rest, TLS in transit, and government-grade storage validation. NetApp remains the only enterprise storage platform validated for top-secret government data.
Certified for NVIDIA DGX SuperPOD, the AFF A70 delivers the NFS/RDMA throughput required for GPU-scale AI training. Concurrent read from massive datasets at 1 TB/s cluster throughput eliminates storage as the bottleneck for LLM and deep learning workloads.
Scale from one HA pair to 24 nodes for a unified NFS/SMB namespace with 330 PB effective capacity — consolidating distributed file infrastructure from multiple legacy NAS systems into a single managed, redundant, all-flash platform.
Sub-millisecond NVMe/FC and NVMe/TCP latency, combined with ONTAP's Oracle and SQL Server certified data management (SnapCenter), delivers consistent performance for the most latency-sensitive OLTP and OLAP database deployments at enterprise scale.
Trusted UK IT reseller since 2003 — supplying businesses of all sizes with genuine, competitively priced technology.
Servnet is an authorised IT reseller with direct access to leading product lines at competitive pricing.
Our engineers will help you select the right product and advise on compatibility with your existing infrastructure.
Most products ship from UK stock. Express delivery available for urgent deployments.
All products are genuine, brand-new, with full manufacturer warranty and RMA support.
We can pre-configure your hardware before shipping — reducing on-site deployment time and cost.
Post-sale support from our certified engineers. We're here if anything goes wrong.
Entry all-flash unified storage — NVMe performance, ONTAP intelligence, at accessible scale
NetApp's most powerful all-flash platform — 14.7 PB raw, 2048 GB memory, 176 PB NAS scale
Pure block storage excellence — symmetric active-active multipathing, NVMe speed, 100% availability guarantee
Capacity-optimised all-flash — high-density NVMe QLC SSDs at the economics of spinning disk
