Lexar unveils AI-focused storage platform at COMPUTEX 2026

2026-06-02 · Source: Dataconomy · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Intermediate, quick

Summary

Lexar unveiled its AI Storage Core vision at COMPUTEX 2026, introducing a suite of AI-aware storage solutions designed for local AI workloads, AI PCs, and high-performance computing. The company highlighted its 5nm Gen5 Storage Processing Unit (SPU) with a DRAM-less architecture and an Intelligent Scheduling engine, which reduces DRAM needs by approximately 40% while enhancing efficiency. New products include the NM1090 PRO 8TB PCIe Gen5 SSD, offering read speeds up to 14,400 MB/s and write speeds up to 13,400 MB/s, suitable for extensive local AI applications. Lexar also showcased AI-grade Gen5 SSD and Storage Stick concepts, aiming for 11GB/s bandwidth, and the PLAY X PCIe 4.0 M.2 NVMe SSD, delivering 7,400 MB/s read and 6,500 MB/s write speeds, now available in Europe and Asia-Pacific.

Key takeaway

For AI Architects designing edge AI systems or AI Engineers deploying local AI models, Lexar's new AI-aware storage solutions offer critical performance enhancements. You should evaluate the NM1090 PRO 8TB PCIe Gen5 SSD for high-resolution media projects and extensive local AI applications, utilizing its 14,400 MB/s read speeds. Consider the AI-grade Gen5 SSD concepts for compact devices needing larger local model storage and improved bandwidth up to 11GB/s to ensure optimal efficiency.

Key insights

Lexar's AI Storage Core vision focuses on high-performance, efficient local storage solutions for the growing demands of edge AI.

Principles

• Local AI requires robust, low-latency storage.
• DRAM-less architecture enhances supply stability.
• Intelligent scheduling optimizes data handling.

In practice

• Use NM1090 PRO 8TB SSD for local AI.
• Consider AI-grade Gen5 SSDs for compact devices.
• PLAY X PCIe 4.0 M.2 NVMe SSD for gaming PCs.

Topics

• AI Storage
• Edge AI
• PCIe Gen5 SSD
• Storage Processing Unit
• Local AI Workloads
• COMPUTEX 2026

Best for: Machine Learning Engineer, Computer Vision Engineer, AI Hardware Engineer, AI Engineer, AI Architect

Related on AIssential

• Micron Readies Client Storage for AI — Local AI on client devices is driving demand for high-performance, power-efficient storage solutions like PCIe Gen5 QLC SSDs.
• Nvidia BlueField-4 STX adds a context memory layer to storage to close the agentic AI throughput gap — Nvidia's BlueField-4 STX architecture optimizes AI agent performance by accelerating KV cache access.
• Liquid-cooled AI systems expose the limits of traditional storage architecture — Hybrid air/liquid cooling for AI infrastructure is inefficient and creates thermal liabilities for storage.
• AMD's tiny AI PC points to a more local future for model inference — Local AI inference on compact hardware reduces cloud dependency, improves privacy, and lowers latency.
• Dell's AI Factory getting supercharged storage - Blocks & Files — Dell's AI Factory expansion integrates advanced storage, compute, and software to accelerate enterprise agentic AI adoption.
• Computex 2026: Are We Heading for the Agentic PC Era Yet? — Computex 2026 signaled a shift from AI PCs to agentic AI and physical AI appliances, emphasizing Taiwan's pivotal role in the electronics value chain.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Dataconomy.