Workstation Of The Deep Learning Elite

This quiet, fast, reliable and universal multi-GPU deep learning workstation beats every other solution on the market

order nowview DATASHEET
trusted by:
GRANDO RM

DEEP learning PRODUCT LINE

The Comino Deep Learning multi-GPU workstation and server line is designed and produced with the one and only focus in mind – that is to allow for the fastest, most efficient and most stable machine learning operation on the market. Our devices are tested with the most popular frameworks, such as PyTorch, TensorFlow and others. Choose Grando ML systems for the best results in deep learning.

GRANDO DL
INSIGHT ™

Multi-GPU Workstation / Server
4x Nvidia A100 80Gb GPUs
1x AMD Threadripper Pro 3995WX CPU
Comino Liquid Cooling
Comino Grando RM Platform

DatasheetBUY NOW
GRANDO DL
THOUGHT ™

Multi-GPU Workstation / Server
4x Nvidia A6000 GPUs
1x AMD Threadripper Pro 3995WX CPU
Comino Liquid Cooling
Comino Grando RM Platform

DatasheetBUY NOW

Talk To Engineer:

Let's talk

Grando DL Product Specifications

Please, contact our sales team In case you want a custom setup
Specs
GRANDO DL
INSIGHT™
GRANDO DL
THOUGHT™
GPU
4x Nvidia A100 80GB
4x Nvidia A6000 48GB
GPU MEMORY
TOTAL: 320GB
TOTAL: 192GB
CPU
AMD Threadripper PRO
3995 WX
AMD Threadripper PRO
3995 WX
SYSTEM POWER USAGE
UP to 3 kW at 100–120 Vac
UP to 3 kW at 100–120 Vac
MEMORY
1024 GB DDR4
1024 GB DDR4
NETWORKING
Dual-port 10Gbase-T shared with BMC, WI-FI 6
Dual-port 10Gbase-T shared with BMC, WI-FI 6
STORAGE OS
DUAL 1.92TB M.2 NVME DRIVE
DUAL 1.92TB M.2 NVME DRIVE
STORAGE DATA/CACHE
DUAL 7.68TB U.2 NVME DRIVE
DUAL 7.68TB U.2 NVME DRIVE
COOLING SYSTEM
DIRECT LIQUID COOLING
DIRECT LIQUID COOLING
SYSTEM ACOUSTICS
<37DB
<37DB
OPERATING TEMPERATURE RANGE
5-40ºC
5-40ºC
SOFTWARE
UBUNTU \ WINDOWS
UBUNTU \ WINDOWS
HEIGHT
439MM
439MM
WIDTH
177MM
177MM
LENGTH
681MM
681MM
CLASS
WORKSTATION / SERVER
WORKSTATION / SERVER
proven performance

overpowering
The competition
In a whisper

According to the Tensorflow benchmarks ran by the respectable Machine Learning professional Harrison Kinsley AKA “sentdex”, Grando DL workstation, while being cooler and quieter, overpowers the Nvidia DGX by 12%. You can watch the video here.

get datasheet
whisper quiet

twice as quiet as Any air-cooled Workstations

If you've ever worked on a powerful air-cooled multi-GPU workstation, you've experienced how exhaustingly loud those can be, when even being in the same room with them can be considered a torture. This is not the case with Grando RM workstations / servers, as they are designed from the ground-up to perform quietly without sacrificing any bit of power. You can watch the comparison video here.

view specs
comino liquid cooling

engineered,
not assembled

Comino designs and engineers its workstations and servers with the client's success in mind, customising the liquid-cooling system to maximise the performance and cooling efficiency, while at the same time minimising the noise output. You succeed, because we design and manufacture 90% of the components of our liquid-cooled systems, and guarantee the performance.

get started
testimonials

Praised by the Top Tech Leaders worldwide

jesse woolston

"The main factor as to why I love the Grando RM is its ability to be diverse with training and modelling, where I can give it any and all assignments and I am able to just utilise the tools and focus on the art".

linus sebastian

"God of computers".
"On this machine, compute take such little time, that I've been having trouble getting all GPUs to get fully loaded".
"It appears to be rock freaking solid stable".

harrison kinsley

"This is the coolest deep learning machine that I have ever had the opportunity to use. It’s the most power in the smallest form factor also, that I’ve ever used, and finally, it also runs the coolest temperatures, that I’ve ever used"

are you ready?

join the elite
of Grando rM Professionals

order grando DL now