Workstation for Businesses – B2B on enquiry, product cannot be returned, AI supercomputer, NVIDIA GB300, 748GB coherent memory, diskless, designed for large language model inference, pre-trained network specialisation and AI agent development, performance of up to 20000TFLOPS FP4, suitable for local processing of AI models, loads and runs models with up to 1 trillion parameters, supports PyTorch, TensorFlow and NVIDIA NIM microservices, ideal for developers, researchers and data scientists, case type: Midi Tower, OS: Linux Ubuntu
GIGABYTE W775-V10-L01-000-3. X 8TB 134,990 € We accept pre-orders
Buy
Benefits of Pre-Orders:
We are guarding the price for you - If the price gets lower when the product is available, the difference will be refunded.
Guaranteed purchase - When the goods are in stock, nobody will snatch your piece.
Priority delivery - With a pre-order, you get a fixed spot on the waiting list. You will be among the first customers to receive the goods.
No worries - You don't have to check the availability, we'll do it for you.
GIGABYTE W775-V10-L01-000-3. X 8TB
ℹ️
This product is intended for business, government and educational institutions only. Completing an order on the e-shop does not constitute a binding contract, but rather a request for a quote.
The sale of this product is subject to export, sanction, and other legal restrictions. Before an order can be accepted, we must verify the buyer, the end user, the country of delivery, and the intended use. The enquiry can only be accepted after successful authorisation by the supplier.
If the required conditions are not met, the request for a quote may be rejected or the order may be cancelled without any claim to the delivery of goods.
If you are interested in purchasing an AI solution or accelerator, you can also email us at [email protected]. We will then prepare a quote and an individual contract for you. For more information, please see our terms and conditions (clauses 3.33 and 3.34).
GIGABYTE W775-V10-L01 workstation
The most powerful AI supercomputer for your desk – data centre performance without the server room
The GIGABYTE W775-V10-L01 is a powerful deskside AI supercomputer built on the NVIDIA DGX Station architecture for data scientists, AI researchers, and developers who need the power of an entire data centre right at their desk. At its core is the NVIDIA GB300 Grace Blackwell Ultra superchip – a combination of the Blackwell Ultra GPU architecture with 252GB of HBM3e memory and a 72-core ARM Grace Neoverse V2 processor with 496GB of LPDDR5X memory, connected by NVLink-C2C technology with a 900GB/s throughput. The result is a 748GB coherent memory space capable of holding and running models with up to 1 trillion parameters locally at up to 20 petaFLOPS in FP4 format – with no cloud dependency, no shared infrastructure, and full control over sensitive data. NVIDIA MIG technology allows the GPU to be partitioned into up to seven isolated instances for an entire AI team to work concurrently, and connecting two stations via an NVIDIA ConnectX-8 SuperNIC with up to 800Gb/s bandwidth doubles the performance to over 1.4TB of coherent memory and 40 petaFLOPS of AI power. The pre-installed NVIDIA DGX OS with CUDA-X libraries, TensorRT, NIM microservices, NVIDIA AI Enterprise, PyTorch, TensorFlow, and NVIDIA OpenShell ensures you can get started instantly without lengthy configuration – all in a Midi Tower chassis measuring 245×595×528.4mm with a 1600W 80 PLUS Titanium certified power supply.
748GB (HBM3e + LPDDR5x)
Coherent memory
Blackwell GB300
Chip architecture
NVIDIA ConnectX
High-speed network card
NVIDIA AI Software Stack
Complete software stack
1600W
Power consumption
Key features of the GIGABYTE W775-V10-L01 workstation
NVIDIA GB300 Grace Blackwell Ultra superchip with Blackwell Ultra GPU (252GB HBM3e, 7.1TB/s) and a 72-core ARM Grace Neoverse V2 processor (496GB LPDDR5X) connected by NVLink-C2C technology with 900GB/s throughput
Up to 20 petaFLOPS of performance in FP4 format and 330 TOPS in Int8 format for training, fine-tuning, and inference of the most demanding AI models
748GB of coherent memory capable of loading and running models with up to 1 trillion parameters locally, without dependency on the cloud or an external server
NVIDIA MIG technology to partition the GPU into up to 7 isolated instances – a powerful local cluster for the entire AI team in a single device
Connect two stations via a ConnectX-8 SuperNIC (up to 800Gb/s) for over 40 petaFLOPS of performance and over 1.4TB of coherent memory
Pre-installed NVIDIA DGX OS with CUDA-X, TensorRT, NIM microservices, NVIDIA AI Enterprise, PyTorch, TensorFlow, and NVIDIA OpenShell for an instant start without configuration
GB300 Grace Blackwell Ultra superchip and 748GB of coherent memory
At the heart of the GIGABYTE W775-V10-L01 is the NVIDIA GB300 Grace Blackwell Ultra superchip – a unique combination of a Blackwell Ultra GPU with 252GB of HBM3e memory and 7.1TB/s throughput, and a 72-core ARM Grace Neoverse V2 processor with 496GB of LPDDR5X and 396GB/s throughput. Both parts of the superchip are connected by NVLink-C2C technology with a 900GB/s bandwidth, which eliminates the traditional bottleneck between CPU and GPU memory to create a single 748GB coherent memory space. The result is 20 petaFLOPS of performance in FP4 format and 330 TOPS in Int8 format – right where an entire server room floor was previously required.
NVIDIA MIG and ConnectX-8 for AI team performance in a single device
The GIGABYTE W775-V10-L01 is not just a personal supercomputer, but a powerful local compute node for an entire AI team. NVIDIA MIG technology partitions the GPU into up to seven fully isolated instances, each with its own dedicated memory, compute cores, and network connection, enabling multiple researchers to work concurrently without impacting one another. Connecting two stations via an NVIDIA ConnectX-8 SuperNIC with up to 800Gb/s bandwidth then doubles the performance to over 40 petaFLOPS and over 1.4TB of coherent memory for working with the largest available models – without the need to build an expensive server cluster.
AI application prototyping and development without limits
The complete NVIDIA AI software stack, combined with NVIDIA OpenShell, provides developers with a full-featured platform for creating AI models, AI agents, and AI-augmented applications – all locally, without cloud dependency. The NVIDIA DGX OS comes pre-configured with CUDA-X libraries, Container Toolkit, Docker, and NVIDIA AI Enterprise for an immediate start to development. Once a solution is ready for production deployment, the GIGABYTE W775-V10-L01 enables direct and seamless migration of workloads to the NVIDIA DGX Cloud or other NVIDIA-accelerated infrastructure – using the same tools, libraries, and pre-trained models.
Fine-tune AI models with billions of parameters right at your desk
Use the GIGABYTE W775-V10-L01 to fine-tune pre-trained models with billions of parameters right at your desk. Training on your own data allows you to specialise AI models for specific industry data or use cases – without sending sensitive data to the cloud or paying for expensive GPU instances. The NemoClaw platform then ensures secure and isolated operation of autonomous AI agents with full governance control. The result is a model tailored precisely to your scenario, created locally, securely, and under your complete control.
GIGABYTE W775 delivers top-tier data science
The combination of 748GB of coherent memory and 20 petaFLOPS of performance makes the GIGABYTE W775-V10-L01 the ideal workstation for demanding data analytics and machine learning projects. Extensive datasets, complex computational models, and demanding training processes that previously required a powerful cloud cluster or dedicated server can now run directly on your desk. Four M.2 NVMe slots – two PCIe 5.0 x2 and two PCIe 6.0 x4 for training data – two 400Gb/s QSFP network interfaces, and three PCIe 5.0 x16 slots ensure data throughput worthy of a research infrastructure – fast, local, and without waiting for remote infrastructure.
Inference of models with up to 1 trillion parameters
The Blackwell Ultra architecture's Tensor Cores, with support for the FP4 format, achieve up to 20 petaFLOPS of performance. Combined with 748GB of coherent memory, this lets you run inference on the largest available AI models with up to 1 trillion parameters directly on your desktop. Test, validate, and deploy models locally and in real time – with no cloud latency, no shared infrastructure, and no risk of sensitive data leaks. NVIDIA NIM microservices then enable the rapid deployment of optimised models as containers for production inference.
AI supercomputer performance
Up to 20 petaFLOPS for FP4 format inference
Up to 1 trillion parameters
Local inference without cloud dependency
Connecting two systems
A cluster for over 40 petaFLOPS of performance and 1.4TB of coherent memory
Ready to work straight away
Pre-installed NVIDIA AI software stack
Memory without compromise
748GB of coherent CPU and GPU memory
Your own data
Fine-tune models with billions of parameters right at your workplace
Generally, the higher the number, the more powerful the processor. For an office PC, a basic processor series will be more than sufficient, but for more challenging work and gaming you will require a more advanced processor.
Počet jadier v procesore ovplyvňuje výkon vášho stolného počítača. Viac jadier znamená väčšie možnosti pre multitasking, rýchlejšie spracovanie náročných aplikácií a celkovo vyššiu výkonnosť. Ako ale zistiť, koľko jadier potrebujete? V tomto článku sa pozrieme na to, čo znamená počet jadier, ako ovplyvňuje výkon vášho desktopu, a poradíme, podľa čoho sa pri výbere orientovať.
Generally, the higher the number, the more powerful the processor. For an office PC, a basic processor series will be more than sufficient, but for more challenging work and gaming you will require a more advanced processor.
Počet jadier v procesore ovplyvňuje výkon vášho stolného počítača. Viac jadier znamená väčšie možnosti pre multitasking, rýchlejšie spracovanie náročných aplikácií a celkovo vyššiu výkonnosť. Ako ale zistiť, koľko jadier potrebujete? V tomto článku sa pozrieme na to, čo znamená počet jadier, ako ovplyvňuje výkon vášho desktopu, a poradíme, podľa čoho sa pri výbere orientovať.
One of the basic parameters of a graphics card. The greater the capacity, the more power potential. Cheaper graphics cards can have, for example, 512 MB, whereas gaming cards can have 4 GB or...
HDD and SSD drives are used for permanent storage of data on computers and laptops. But what are the differences between the two, and what are their advantages?
USB 3.0 is 10 times fater than its predecessor (with which it is backwards compatible). The maximum data transmission speed can be used with flash drives, portable drives and external drives that...
Determines the generation and speed of technology that directly connects several graphics cards together. This connection allows them to efficiently share data and memory, which accelerates computations in the field of artificial intelligence.
NVLink-C2C
NVLink bandwidth
900 GB/s
More Specifications
SIL Servis Partner a.s., Těšínská 1970/56, 710 00 Slezská Ostrava, Czech Republic, +420 552 301 141, [email protected]
Gigabyte, founded in 1986, is an irreplaceable player in the field of computer components. They put great emphasis on key technologies and the strictest quality standards. The company produces a wide range of basic computer components such as motherboards and graphics cards, but also have many computer peripherals, laptops, tablets, desktops and even network solutions and servers on offer. Recently they also introduced a line of Gigabyte mobile phones.
Try our cookiesAlza.cz a. s., Company identification number 27082440, use cookies and other data to ensure the proper functioning of the website and, with your consent, also, among other things, to personalize advertising and the content of our websites. By clicking on the “I understand“ button, you agree to the use of cookies and the transfer of data regarding the behavior on the website for displaying targeted advertising on social networks and advertising networks on other websites.
We use 8 categories of cookies on our website:
Technical cookies
These are strictly necessary for the functioning of the website and the features you choose to use. Without them, our website would not work; you wouldn't be able to log in to your user account, for example.
Functionality cookies
These cookies allow us to remember your basic choices and improve the user experience. These include remembering your preferred language or allowing you to stay logged in permanently.
Social media cookies
These cookies allow us to easily link you to your social media profile and, for example, allow you to share products and services with your friends and family.
Content personalisation
These cookies allow us to show you content and ads according to the information we have about you to best meet your needs. This includes what content you have viewed, or on what device you are accessing our website.
Non-personalised advertising
These cookies allow us to show you general ads for products and services.
Personalised advertising
Thanks to these cookies, we and our partners can offer you relevant products and services based on your purchases, your shopping behaviour and your preferences.
Audience metrics
These cookies allow us to optimise our site for your convenience based on how you use it. The aim is to remember or anticipate your choices. This includes, for example, the use of features, their location, or the behaviour on the page.
By giving your consent to the processing of cookies, functionality and analytical cookies will be installed on the device you use to browse the website (click on the "I understand" button for both categories, or you can select only one of the categories by clicking on the "Settings" button). We always install technical cookies on your device, even without your explicit consent, because without them our website would simply not work.
You can revoke your consent to the processing of cookies. In connection with our company's cookie processing, you also have the following rights: the right to access cookies, delete, modify, supplement and correct them, restrict processing and the right to lodge a complaint with the Office for Personal Data Protection. Read more about your rights.