Skip to content
Server with 8× NVIDIA RTX PRO 6000 Blackwell Server Edition 96 GB

Server with 8× NVIDIA RTX PRO 6000 Blackwell Server Edition 96 GB

Eight passive 96 GB GDDR7 Blackwell PCIe GPUs, 768 GB in total; chassis and configuration agreed per order

Model
RTX PRO 6000 Blackwell Server Edition 8-GPU Server
Condition
New, original packaging
Other names
NVIDIA RTX PRO Server
Quantity
Ask on WhatsApp

Price on request. Tell us the quantity and destination and we reply within one working day.

How we supply this item

Supplied through licensed partners. Server, networking and data-centre hardware is supplied through licensed partners of InTechnologies FZCO. The partner issues the contract and invoice; we handle sourcing, consolidation in Dubai and delivery coordination. Export compliance

Export compliance. This product is subject to US export regulations. How we handle it is described on the export compliance page. Export compliance

This is a PCIe GPU server populated with eight NVIDIA RTX PRO 6000 Blackwell Server Edition cards. Each passively cooled dual-slot card has 96 GB of GDDR7 with ECC, 1,597 GB/s of memory bandwidth, 24,064 CUDA cores, 752 fifth-generation Tensor Cores and 188 fourth-generation RT Cores, with board power configurable up to 600 W. Eight cards give 768 GB of GPU memory in one server. The cards connect over PCIe 5.0 rather than NVLink, which makes the system a strong fit for inference, fine-tuning of mid-sized models, rendering, simulation and virtual workstations, where each GPU or partition works on its own task.

Because it is a full graphics GPU, the same server can run LLM inference by day and rendering or VDI with NVIDIA vGPU at night, and Multi-Instance GPU splits each card into up to four isolated instances. OEMs build such servers in 4U and larger chassis, including NVIDIA RTX PRO Server designs with ConnectX-8 SuperNIC networking; the chassis, processors, memory, storage and network adapters are chosen per order.

InTechnologies FZCO sources these servers, and the RTX PRO 6000 Server Edition cards on their own, for business customers in the UAE, the GCC and Central Asia. Contracts and invoices are issued by our licensed partners; we handle sourcing, consolidation in Dubai and DDP or DDU delivery. Professional Blackwell GPUs are subject to US export regulations, and we verify the end user before accepting an order.

Specifications

Server with 8× NVIDIA RTX PRO 6000 Blackwell Server Edition 96 GB: Specifications
GPUs8× NVIDIA RTX PRO 6000 Blackwell Server Edition
GPU memory96 GB GDDR7 with ECC per GPU, 768 GB in total
Memory bandwidth1,597 GB/s per GPU
CUDA / Tensor / RT cores24,064 / 752 (5th gen) / 188 (4th gen) per GPU
GPU interfacePCIe 5.0 x16, no NVLink
GPU powerUp to 600 W per GPU, configurable; passive cooling
Server vendor and chassis—
Processors—
System memory—
Storage—
Network adapters—

— the vendor, chassis and these components are agreed per order. Message us your workload, quantity and rack power, and we will send the configurations we can supply. Ask on WhatsApp

Questions buyers ask

Why are the vendor, CPU and memory shown as a dash?

The configuration is agreed per order: several OEMs build eight-GPU servers for these cards, with different chassis, power and networking. Send us a message with your workload and quantity, and we will propose the builds we can supply.

Can I buy fewer than eight cards, or the cards alone?

Yes. Servers with two or four cards are common, and the RTX PRO 6000 Blackwell Server Edition is also available as a separate card for your own servers.

How does this compare with an HGX H200 or B300 server?

HGX servers use SXM GPUs with HBM memory joined by NVLink, which suits training of large models. This server uses PCIe cards with GDDR7 and no NVLink: less bandwidth between GPUs, but more flexibility and graphics, vGPU and rendering support.

Is this server export-controlled?

Yes. RTX PRO 6000 Blackwell GPUs fall under US export regulations, and we verify the end user and destination before confirming an order.

NVIDIA

NVIDIA HGX H200 8-GPU Server

Eight H200 SXM GPUs with 141 GB HBM3e each on NVLink; chassis and configuration agreed per order

NVIDIA

NVIDIA HGX B300 8-GPU Server

Eight Blackwell Ultra SXM GPUs with 2.1 TB HBM3e on NVLink 5; chassis and configuration agreed per order