RTX Pro 6000 Blackwell Server Edition 96GB
1,00€
Delivery will be made from 21 days. Free Shipping for orders $1000+
10 in stock
RTX Pro 6000 Blackwell Server Edition 96GB. Server Blackwell edition, 96GB, for data centers/AI training. Direct import, vendor warranty, enterprise invoices, delivery 7–10 days.
Product description
Direct import from the USA and Europe without intermediaries. Best price in Europe. Official warranty 1-3 years RTX Pro 6000 Blackwell Server 96GB
The RTX Pro 6000 Blackwell 96GB series from NVIDIA includes three models: Workstation Edition, Max-Q Workstation Edition, and Server Edition. All of them are built on the latest NVIDIA Blackwell architecture and equipped with 96 GB of GDDR7 video memory with ECC. However, each modification is optimised for different usage scenarios, and it is in these details that the key differences lie.
Each graphics card has 24,064 CUDA cores and supports all current graphics and computing APIs, from DirectX 12 and Vulkan to CUDA 12.8. This makes the series suitable for graphics visualisation as well as deep learning, simulation, big data analysis, and generative AI. However, the way in which cooling, power consumption, performance and dimensions are implemented determines its specialisation.
Specifications
- GPU memory: 96GB GDDR7
- GPU architecture: NVIDIA Blackwell
- NVIDIA CUDA cores: 24064
- Tensor cores: 5th generation
- Ray tracing cores: 4th generation
- AI performance: 4000 AI TOPS
- Single-precision performance: 125 TFLOPS
- RT core performance: 380 TFLOPS
- Memory interface: 512-bit
- Memory bandwidth: 1792 GB/s
- System interface: PCIe 5.0 x16
- Display connectors: 4x DisplayPort 2.1b
- Maximum number of simultaneously connected displays: 4x 4096 x 2160 @ 120 Hz, 4x 5120 x 2880 @ 60 Hz, 2x 7680 x 4320 @ 60 Hz
- Video encoders: 4x NVENC (9th generation), 4x NVDEC (6th generation)
- MIG support: up to 4x 24GB, up to 2x 48GB, up to 1x 96GB
- Power consumption: 600W
- Power connector: 1x PCIe CEM5 16-pin
- Cooling system: Throughflow
- Form factor: 5.4‘ H x 12’ L, dual-slot, extended height
- Graphics APIs: DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
- Computing APIs: CUDA 12.8, OpenCL 3.0, DirectCompute
Server Edition: computing accelerator for data centres and AI infrastructure
Modification without video outputs, with passive cooling and power consumption from 400 to 600 W. This is not a ‘video card’ in the usual sense, but a specialised accelerator for servers that utilises the power of 5th generation tensor cores. It features Multi-Instance GPU support and full integration with virtualisation and NVIDIA AI Enterprise. It allows you to process the largest LLM models and run clusters of dozens of such GPUs.
Where it is used: in AI centres, data centres, render farms, and in tasks where density and scalability are important.
How to choose the right version of the RTX Pro 6000 Blackwell 96GB?
- Need maximum performance on a local machine? — choose the Workstation Edition.
- Looking for a balance between power and thermal package? — Max-Q Workstation is the perfect fit.
- Working on large-scale AI projects or building server infrastructure? — Server Edition is your choice.
All three cards are equipped with the latest NVIDIA technologies, support DisplayPort 2.1, feature GDDR7 ECC memory, and offer high computing density.
Why should you buy the RTX Pro 6000 Blackwell 96GB from us?
- Direct delivery from the USA — no middlemen, no compromises.
- 3-year warranty — reliability from day one.
- Any form of payment. Card, bank transfer (w/ex VAT), USDT cryptocurrency..
- We will help you choose the right version for your task — from rendering to AI.
Order the RTX Pro 6000 Blackwell 96GB right now and get a professional tool that will take your project to the next level.
Additional information
Weight | 1,95 kg |
---|---|
Dimensions | 305 × 137 cm |
Country of manufacture | Taiwan |
Manufacturer's warranty (months) | |
Model | RTX Pro 6000 Blackwell |
Graphics Processing Unit (Chip) | |
Technological process | 4 nm |
Architecture | Blackwell |
Number of CUDA cores | 24064 |
Number of Tensor cores | 752 |
Number of RT cores | 188 |
GPU Frequency (MHz) | 1590 |
GPU Boost Frequency (MHz) | 2617 |
Video memory size (GB) | 96 |
Memory type | GDDR7 ECC |
Memory frequency (MHz) | 28000 |
Memory bus width (bits) | 512 |
Memory Bandwidth (GB/s) | 1597 |
Cache L1 (KB) | 24576 |
Cache L2 (MB) | 128 |
Connection interface (PCIe) | PCIe 5.0 x16 |
FP16 performance (TFLOPS) | 126 |
FP32 performance (TFLOPS) | 1.721 |
FP64 performance (TFLOPS) | 1.721 |
NVENC / NVDEC number of blocks | 4×NVDEC, 4×NVENC |
Cooling type | Passive (server module) |
Number of occupied slots (pcs) | 2 |
Temperature range (°C) | 0–50 |
Multi-GPU support | Yes, via PCIe/Sync, but without NVLink |
Virtualization/MIG support | vGPU support, not MIG |
Width (mm) | 137 |
Length (mm) | 305 |
Weight (kg) | 1.95 |
Product reviews
Only logged in customers who have purchased this product may leave a review.
Reviews
There are no reviews yet.