Close

GPU COMPUTING

Workstations and Servers

for Scientific Research

CryoEM - CryoET - Molecular Dynamics - AI

We are specialists in GPU computing for

Cryo-EM, Cryo-ET, Molecular Dynamics, Computational Chemistry and 

Deep Learning Applications, such as  Alphafold3, Boltz2

GeForce RTX 5090 32GB (Blackwell)

21760

2010 MHz

2410 MHz

680

32GB GDDR7

512-bit

1792 GB/sec

575 W

3.5

GeForce RTX 5080 16GB (Blackwell)

10752

2300 MHz

2780 MHz

336

16GB GDDR7

256-bit

960 GB/sec

360W

3

GeForce RTX 5070Ti 16GB (Blackwell)

8960

2295 MHz

2452 MHz

280

16GB GDDR7

256-bit

896 GB/sec

300W

2.5

NEW ! Blackwell "PRO" Family Nvidia GPUs

4 GPU Workstations and Servers
Nvidia Profesional Blackwell cards

NVIDIA RTX 4500 (32 GB)
PRO Blackwell

Specifications

Architecture NVIDIA Blackwell Architecture
Foundry TSMC
Process Size 4N NVIDIA Custom Process
Transistors 45.6 Billion
Die Size 378 mm²
CUDA Parallel Processing Cores 10,496
NVIDIA Tensor Cores 328
NVIDIA RT Cores 82
GPU Memory 32 GB GDDR7 with ECC
Memory Interface 256-bit
Memory Bandwidth 896 GB/s
Max Power Consumption 200W
Graphics Bus PCI Express 5.0 x16
Display Connectors DP 2.1 (4)
Form Factor 4.4” H x 10.5” L, FHFL Dual Slot
Product Weight 1.070 kg
Thermal Solution Blower Active fan
NVIDIA® 3D Vision® and 3D Vision Pro Support Via 3-pin Mini DIN
Frame Lock Compatible (with NVIDIA RTX PRO Sync)
Power Connector 1x PCIe CEM5 16-pin
NVENC | NVDEC | JPEG 2x | 2x | 1x

NVIDIA RTX 5000 (48 GB)
PRO Blackwell

Specifications

Architecture NVIDIA Blackwell Architecture
Foundry TSMC
Process Size 4N NVIDIA Custom Process
Transistors 92.2 Billion
Die Size 750 mm²
CUDA Parallel Processing Cores 14,080
NVIDIA Tensor Cores 440
NVIDIA RT Cores 110
GPU Memory 48 GB GDDR7 with ECC
Memory Interface 384-bit
Memory Bandwidth 1344 GB/s
Max Power Consumption 300W
Multi-Instance GPU Up to 2x 24GB / Up to 1x 48GB
Graphics Bus PCI Express 5.0 x16
Display Connectors DP 2.1 (4)
Form Factor 4.4” H x 10.5” L, FHFL Dual Slot
Product Weight 1.219 kg
Thermal Solution Blower Active Fan
NVIDIA® 3D Vision® and 3D Vision Pro Support Via 3-pin Mini DIN
Frame Lock Compatible (with NVIDIA RTX PRO Sync)
Power Connector 1x PCIe CEM5 16-pin
NVENC | NVDEC | JPEG 3x | 3x | 1x

NVIDIA RTX 6000 PRO (96 GB)
PRO MAX-Q Blackwell

Specifications

Architecture NVIDIA Blackwell Architecture
Foundry TSMC
Process Size 4N NVIDIA Custom Process
Transistors 92.2 Billion
Die Size 750 mm²
CUDA Parallel Processing Cores 24,064
NVIDIA Tensor Cores 752
NVIDIA RT Cores 188
GPU Memory 96 GB GDDR7 with ECC
Memory Interface 512-bit
Memory Bandwidth 1792 GB/s
Max Power Consumption 300W (NVIDIA RTX Power Guidelines (PDF))
Multi-Instance GPU Up to 4x 24GB
Up to 2x 48GB
Up to 1x 96GB
Graphics Bus PCI Express 5.0 x16
Display Connectors DP 2.1 (4) (NVIDIA RTX Display Resolution Support (PDF))
Form Factor 4.4” H x 10.5” L, FHFL Dual Slot
Product Weight 1.23 kg
Thermal Solution Blower Active Fan
NVIDIA® 3D Vision® and 3D Vision Pro Support Via 3-pin Mini DIN
Frame Lock Compatible (with NVIDIA RTX PRO Sync)
Power Connector 1x PCIe CEM5 16-pin
NVENC | NVDEC | JPEG 4x | 4x | 4x

CONFIGURED software

 

AMBER 25

Molecular Dynamics

AMBER is a premier suite of programs for molecular dynamics simulations of biomolecules. At Linuxvixion, we provide Amber24 fully pre-installed and fine-tuned, benefiting from our direct collaboration with developer Prof. Ross Walker. By harnessing the power of our high-end GPU workstations, we deliver the world’s fastest desktop molecular dynamics solutions.

relion-xxx-600

RELION 5

Cryo-EM Framework

Developed by the Scheres Group at the MRC Laboratory of Molecular Biology, the RELION framework has transformed the field of Cryo-Electron Microscopy (Cryo-EM). Linuxvixion offers RELION 5.0.1 pre-configured and optimized for maximum throughput, facilitating high-speed image processing and macromolecular 3D reconstruction.

MinKNOW: Real-Time Genomic Control & Analysis

The Essential Operating Software for Oxford Nanopore Sequencing.

MinKNOW is the core software driving the entire nanopore sequencing process. It transforms raw electrical signals into actionable genetic data through an intuitive, real-time interface, providing researchers with immediate insights into their experiments.

Key Capabilities:

  • Total Hardware Control: Manage flow cell health, pore calibration, and temperature regulation for consistent results.
  • Real-Time Data Acquisition: Capture high-fidelity signal data directly from MinION and PromethION devices.
  • GPU-Accelerated Basecalling: Integrated with the Dorado engine to translate raw signals into DNA/RNA sequences instantly.
  • Instant Quality Feedback: Monitor read length, Q-scores, and sequencing depth on the fly.

Optimized by LinuxVixion

Our workstations are specifically engineered to handle the massive data throughput of MinKNOW. By integrating Dual NVIDIA RTX 5090 GPUs and the latest AMD Threadripper processors, we eliminate computational bottlenecks, enabling Super High Accuracy (SUP) basecalling in real-time.

Developer: Oxford Nanopore Technologies OS Support: Ubuntu / LinuxVixion Certified

GROMACS

High-Performance Molecular Dynamics

GPU ACCELERATED

GROMACS is a world-leading package for molecular dynamics, designed for simulations of proteins, lipids, and nucleic acids. It is renowned for its extreme efficiency and ability to scale across massive computational resources.

Advanced Simulation

Perform complex biomolecular simulations with state-of-the-art force fields and unprecedented precision.

Unmatched Speed

Highly optimized algorithms for both CPU and GPU execution, delivering more nanoseconds per day (ns/day).

Key Features:

  • 🧬 Versatility: Ideal for everything from simple polymers to complex biological membrane systems.
  • Fast Fourier Transform: Efficient PME (Particle Mesh Ewald) calculations optimized for NVIDIA CUDA.
  • 📊 Integration: Native support for advanced analysis tools and visualization software like VMD or PyMOL.
5090

LinuxVixion Workstation Power

GROMACS thrives on GPU performance. Our workstations, equipped with Dual RTX 5090 GPUs, offer the massive floating-point performance required for high-throughput screening and long-timescale simulations.

Certified for Ubuntu 24.04 LTS & NVIDIA Driver 580+ with CUDA 13 optimization.

DEEP LEARNING STACK

Ollama • Open WebUI

In the era of Generative AI and LLMs, hardware is only half the equation. Linuxvixion workstations ship with a production-ready AI environment on Ubuntu 24.04 LTS. We pre-configure the proprietary NVIDIA drivers, CUDA toolkit, and the NVIDIA Container Toolkit.

  • Ollama Engine: Configured and running, ready to pull and execute Open Source models locally.
  • Open WebUI: A ChatGPT-like graphical interface connected to Ollama, so your team can test models immediately through a web browser.
  • Data Science Workspace: A JupyterLab container environment pre-loaded with the necessary Python libraries (LangChain, CrewAI, ChromaDB), ready for your developers.

SOME OF OUR CUSTOMERS

OUR GPU SYSTEMS IN EUROPE

We configure any software you need 

in order you start using it as you open the box

It has never been easier to work on your server remotely

This website uses cookies to ensure you get the best experience on our website. If you want to know more or withdraw your consent to all or some of the cookies, please refer to the Privacy Policy. By closing this banner, you agree to the use of cookies.​