Contact

AI & HPC

Feed the GPUs.

Large datasets and sustained throughput. maxRAID and maxRAID Grid keep data moving for training, checkpoints and analytics.

Talk to an engineer Start free trial

20GB/s

Per Grid storage pool, read and write1

200GB/s

Striped across ten 8+2 pools: ten nodes with ten SSDs each1

Built to keep GPUs busy.

Predictable latency.

Performance stays predictable as the array fills — keep some free space for the best results.

Sequential at the media.

Every write reaches the SSDs as a large sequential stripe — well suited to datasets and checkpoints.

GPUDirect ready.

maxRAID Grid speaks NVMe‑oF over TCP and RDMA, with GPUDirect and shareable multi‑mount volumes.

Resilient at scale.

Node and drive failures handled automatically, with full‑speed writes in degraded mode.

Recommended

The right tools for the job.

Available now

maxRAID

RAID, rebuilt for flash.

Software RAID for SSDs. RAID‑10 speed with parity efficiency, longer drive life and inline compression.

Learn more
Beta Q4 2026

maxRAID Grid

Performance at any scale.

Scale‑out block storage built for cloud providers and AI workloads. Self‑healing, on your own hardware.

Learn more

See it on your own hardware.

Try maxRAID free for 120 days, on arrays up to 100 TB.

Start free trial Talk to an engineer
  1. maxRAID Grid is pre‑release; performance figures are design targets, provided the network can carry the traffic.