564kW 80-Slot Immersion Cooling Container (20ft)
Enterprise-grade platform, assembled and tested in the EU.
Overview
A 20-foot container carrying 80 slots at 564 kW — the compact end of the containerised immersion range, for sites where a 40-foot unit will not fit or where capacity is being added in smaller increments.
Half a megawatt is an awkward size to build conventionally: too large for a room, too small to justify a building. Containerised, it becomes a single purchase order with a known delivery date. Operators often buy two or three of these rather than one 40-foot unit precisely because capacity can then track demand instead of preceding it.
Why teams choose it
- 564 kW, 80 slots — compact containerised capacity.
- 20-foot footprint — fits sites where a 40ft unit will not.
- Incremental scaling — add capacity as demand appears.
- Fully integrated — tanks, circulation, rejection and distribution included.
Typical applications
- Sites with restricted footprint or access
- Incremental capacity growth
- Mid-size AI compute or mining deployments
What you get from Kentino
Kentino supplies, configures and supports this system as part of a complete deployment: layout planning, fluid volume and heat-rejection sizing, power design, EU-based logistics and warranty. If you are cooling GPU hardware rather than ASICs, our engineers will confirm compatibility and specify the loop before you order.
Lead time and freight are quoted per project. Dielectric fluid is priced separately — contact us for a full bill of materials and a delivery estimate to your site.
The questions buyers ask us most often before ordering a server.
How long does it take?
Machines built from components we hold ship quickly; anything requiring a specific GPU generation depends on supply. We give you a date before you pay, and if it moves we tell you rather than letting you find out.
Can the configuration be changed before you build it?
Almost always. GPUs, memory, storage and cooling are chosen per order, and the listed configuration is a starting point rather than a fixed package. If you need more VRAM, faster storage or a different cooling approach, say so before you order and we will quote the change.
Can I collect the server in person?
You can. Our warehouse is in Prague, and collection in person is welcome — most people who come use the visit to go through the machine with our engineer and ask the questions that are awkward over email. For orders within the Czech Republic we also try to deliver personally and walk you through the setup on site.
Can I talk to someone who actually understands the workload?
Yes. We have an engineer who works on AI systems specifically, not a general sales desk. If your question is about batch sizes, quantisation, interconnect or where your bottleneck will be, ask it — that conversation usually changes the configuration for the better.
Which model can I run on this configuration?
Yes. Every machine is assembled, burn-in tested and benchmarked on real AI workloads before it ships, and it leaves us with an LLM already installed and running. You plug it in, connect it to your network and start work — the only decision left is which project it runs first.
How do you test a server before shipping?
We run it against actual AI workloads rather than synthetic scores: inference throughput, sustained load behaviour and thermals under continuous operation. You get the benchmark results with the machine, so the performance you were promised is the performance you can verify on day one.
Is the server ready to run when it arrives?
Yes. Every machine is assembled, burn-in tested and benchmarked on real AI workloads before it ships, and it leaves us with an LLM already installed and running. You plug it in, connect it to your network and start work — the only decision left is which project it runs first.
Ships from our EU warehouse. Heavy items may require freight arrangement — contact us for a shipping quote and lead time. 2-year limited warranty with advanced RMA support; extended warranty available.
Not exactly what you need?
Tell us your workload and we'll spec this platform around it — GPUs, memory, storage and cooling matched to what you actually run.