商店現已上線

我們打造用於網站、AI 智慧體和 LLM 訓練的 Workstation AI 機器——線上配置併購買。

獲取同行價格
AI 產品
AI 實驗室OpenAI 智慧體Claude 代理Grok BotWorkstation AI 原生 CRM營銷所有產品
AI 解決方案
應用型 AIAI 智慧體生成式 AIAI 自動化AI 技能提升中小企業 AI 套餐企業 AI 實驗室AI 工作站NVIDIA 硬體與軟體NVIDIA 加速計算私有 AIGPU 私有云GPU 叢集邊緣 AI行業 AI
AI 服務
平臺現代化數字工程資料基礎與 AI自主運營AI 諮詢DevOps 自動化網路安全軟體開發智慧體構建MLOps 搭建GPU 租賃GPU 私有云
關於我們
公司我們的故事合作伙伴客戶案例
AI 資料中心
AI 資料中心GPU 私有云GPU 叢集GPU 租賃
AI 洞察Jev 系列基準測試實驗室模型選擇
技術說明
文件
Linux 作業系統UbuntuRed Hat Enterprise LinuxSUSE LinuxAlpine LinuxDebian、Rocky 與 AlmaLinux
AI 雲平臺AWS 與 Amazon BedrockGoogle Cloud 與 Vertex AIMicrosoft Azure 與 AI FoundryGPU 雲與算力市場
私有 AI 資料中心面向律師事務所面向會計師事務所本地部署平臺全面安全的雲
工具Ring PromoterJobshout
新聞
部落格
聯絡我們登入

面向現代企業的 AI 工作站、AI 多智慧體軟體、GPU 基礎設施和智慧代理解決方案。

聯絡我們

AI 解決方案

應用型 AIAI 智慧體生成式 AIAI 自動化AI 技能提升中小企業 AI 套餐企業 AI 實驗室行業 AI

產品

所有產品Workstation AI native CRM 與 ERP營銷OpenAI 智慧體Ring PromoterJobshout

公司

關於我們公司AI 資料中心為什麼選擇Workstation合作伙伴客戶案例定價聯絡TenthMatrix

資源

AI 洞察技術說明文件Linux 作業系統AI 雲平臺私有 AI 資料中心部落格搜尋網站地圖
英國總部
77-79 Marlowes, Hemel Hempstead HP1 1LF路線指引 — 從 M25 外環倫敦 20 號出口駛出公司編號: 11641870週一至週五:上午 9:00 - 下午 6:00 GMT
+44 7515 356 146
比利時辦公室
Workstation SRL, Rue Vanderkindere 34, 1180 Uccle, BrusselsBE 0751.518.683週一至週五:上午 9:00 - 下午 6:00 CET
+32 492 45 67 46
印度辦公室
#159 Sector 9, Pocket 1, DDA Flats, 110077 Dwarka, New Delhi
+91 98881 98841
台灣辦公室
3F, No. 2-4, Aisi Rd., Ren'ai Dist., Keelung City 200, Taiwan基隆市仁愛區愛四路2之4號3樓週一至週五:上午 9:00 - 下午 6:00 臺灣時間(GMT+8)
+886 926 892 701+32 492 45 67 46

© 2026 Workstation AI。保留所有權利。

隱私資料刪除Cookie服務條款網站地圖

NVIDIA、NVIDIA 標誌、RTX、RTX PRO、Blackwell、CUDA、NVLink、MGX、Omniverse、Spectrum-X、Quantum、BlueField、DGX 與 HGX 為 NVIDIA Corporation 在美國及其他國家的商標及/或註冊商標。AMD、AMD Arrow 標誌、EPYC、Instinct、Ryzen 與 Threadripper 為 Advanced Micro Devices, Inc. 的商標。Dell 與 PowerEdge 為 Dell Inc. 或其子公司的商標。Intel 與 Xeon 為 Intel Corporation 或其子公司的商標。AMAX、AceleMax 與 LiquidMax 為 AMAX Engineering Corporation 的商標。所有其他產品名稱、標誌與品牌均為其各自所有者之財產。我們使用它們僅為識別我們所描述、供應或支援的產品;使用這些名稱並不表示其所有者為我們背書。

Loading blog...

首頁 / 部落格
NvidiaGPUAI FactoryData CentreHardwareAI

NVIDIA Blackwell Ultra B300 Has Landed in the UK: Configure Yours Today

Eight Blackwell Ultra GPUs, 288 GB of HBM3e each: size it with the AI Sales Engineer, take your Trade discount and secure your build slot

Balinder Walia2026年11月7日3 min read
NVIDIA Blackwell Ultra B300 has landed in the UK: eight GPUs, 288 GB of HBM3e each.

NVIDIA's Blackwell Ultra B300 systems have arrived with our UK distribution partners. If you have been waiting for the most capable eight-GPU platform NVIDIA makes, the wait is nearly over. You can configure, price and order yours today, without a sales call.

NVIDIA Blackwell Ultra B300 has landed in the UK: eight GPUs, 288 GB of HBM3e each, 144 PFLOPS of FP4.

In one sentence. B300 is landing in the UK: ask our AI Sales Engineer to size and price your build in minutes, take your Trade discount, and order today to secure your build slot.

What B300 brings

Blackwell Ultra is NVIDIA's step up from B200, built for the two jobs that matter most right now: training large models and serving reasoning models to many users at once. An eight-GPU HGX B300 system gives you:

  • 288 GB of HBM3e on every GPU, over 2 TB in one system. Large models, long contexts and big batches fit in GPU memory instead of being split across machines.
  • Up to 144 PFLOPS of FP4 and 72 PFLOPS of FP8 (NVIDIA's sparse figures for HGX B300), for fast inference and efficient training.
  • Fifth-generation NVLink at 1.8 TB/s per GPU, so the eight GPUs behave like one very large accelerator.
  • 800 Gb/s ConnectX-8 networking per GPU, ready to scale from one node to a full AI factory.

Who it is for

  • AI companies and research teams training or fine-tuning frontier-scale models.
  • Enterprises serving reasoning models and agents to thousands of staff or customers, on infrastructure they own.
  • Data centre and GPU cloud operators adding the newest capacity their customers are asking for.

Configure yours in minutes with the AI Sales Engineer

You don't need to wait for a quote by email. Our AI Sales Engineer knows the B300 platforms in our catalogue, reads their specifications and compatibility rules, and prices every configuration from our live pricing engine. It never quotes a number it didn't get from the catalogue.

  1. Tell it what you are building: the models, their sizes and precision, how many users, and where the system will live.
  2. Get a build: GPUs, CPUs, memory, storage and networking, with the trade-offs explained, plus power and rack requirements.
  3. Get it priced: it can add the system to your basket, create a PDF quote, or take you straight to checkout. You confirm every step.

Prefer to start from the hardware? Open the NVIDIA-Certified HGX B300 server (eight Blackwell Ultra GPUs, 3 TB of DDR5, ConnectX-8 and BlueField-3, priced online) or the HGX B300 8-GPU server (priced on quote), and press Ask the AI about this system on either page. Planning more than one node? Our AI data centre planner sizes the rack, the power and the timeline in two minutes.

Take your Trade discount

Buying for a business? Workstation Trade pays for itself on an order this size:

  • Money off qualifying orders, taken off before you pay. Join at checkout and the discount applies to the order you join with.
  • 60-day price lock on quotes, so your B300 price holds while you get sign-off.
  • An AI engineer on call for sizing, deployment and the software stack.

The Trade route planner shows exactly what you save on your order in four quick steps.

Order today, secure your slot

Demand for Blackwell Ultra is strong. Each system is built to order, and the lead time is confirmed when you order. Orders placed now are first in line as UK supply arrives.

  • Configure and price your B300 with the AI Sales Engineer →
  • Open a Trade account and save →
  • Talk to an engineer about a multi-node cluster →

Prices on shop.workstation.co.uk are ex VAT. Performance figures are NVIDIA's published HGX B300 specifications.