Kentino AI 288 Rome L40 — 6× NVIDIA L40 Passive Enterprise (288 GB ECC VRAM) 2000W

Kentino AI 288 Rome L40 — 6× NVIDIA L40 Passive Enterprise (288 GB ECC VRAM) 2000WK AI 288 Rome L40 2172TOPS 288 GB ECC VRAM Enterprise Server 6x NVIDIA L40 Passive EPYC Milan 2 172 TOPS INT8 2 172 TOPS INT8 288 GB ECC VRAM pool ECC end to end 24 7 production rated Published external references. Not measured on Kentino hardware. A 4U rack mount enterprise inference server with six NVIDIA L40 Ada Lovelace passive datacenter cards (48 GB ECC each) pooled to 288 GB ECC VRAM, one AMD EPYC 7643 Milan CPU (48C 96T), 384 GB DDR4 2666 ECC,

9kg Connection ethernet Voltage input 12V DC Operating temperature 0~35 ℃ Kaspa calculator

no tensor-parallel overhead CPU AMD EPYC 7643 Milan (48C/96T

Dual PSU for split power delivery — each PSU feeds a portion of the system

The 4TB variant is ideal for teams working with large training datasets or maintaining extensive model libraries locally

Four slots populated — three free for NIC / storage / telemetry

At an efficiency of 9

0 + ControlNet + AnimateDiff stacks x 4

Maximum storage capacity for large datasets and model libraries

omsh-card{border:1px solid var(--line)

With a power of 450 MH/s and a consumption of only 240 W

10 Low OneMiners Stack Cheap power Zero fees Long-term contracts Financial Tools Pay-later Calculators Conclusion 👉 ROI is determined before you even plug in the miner

Avalon (Canaan) seeks to advance the world we live in