NVIDIA RTX 4500 Ada 24GB (900-5G132-2260-000)
P/N: 900-5G132-2260-000
3 047 € (inc. VAT (Spain))
New
NVIDIA RTX Pro 6000 Blackwell Server Edition 96GB (900-2G153-0000-000)
P/N: 900-2G153-0000-000
11 528 € (inc. VAT (Spain))
EU Delivery time is made within 3-7 days
This is an estimated timeframe. Delivery times may vary depending on logistics and stock availability.
Warranty 2 year
The product is covered by the manufacturer’s standard warranty.
In stock
Guaranteed Safe Checkout:
RTX Pro 6000 Blackwell Server Edition 96GB. with fast EU delivery and worldwide shipping. Includes official warranty.
Expert support On-line
Our specialist will help you choose the right server components and ensure full compatibility with your system.
Technical Specifications Product
| Weight | 3,42 kg |
|---|---|
| Dimensions | 30,5 × 13,7 × 17 cm |
| Country of manufacture | Taiwan |
| Manufacturer's warranty (years) | 1 |
| Model | RTX Pro 6000 Blackwell |
| Cache L2 (MB) | 128 |
| Cache L1 (KB) | 24576 |
| Process technology (nm) | 4 |
| Memory type | GDDR7 ECC |
| Graphics Processing Unit (Chip) | |
| 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 frequency (MHz) | 28000 |
| Memory bus width (bits) | 512 |
| Memory Bandwidth (GB/s) | 1597 |
| Connection interface (PCIe) | PCIe 5.0 x16 |
| FP16 performance (TFLOPS) | 126 |
| FP32 performance (TFLOPS) | 62.5 |
| 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 |
| SKU | 900-2G153-0210-300 |
| Architecture | Blackwell |
Product description
Direct import from the USA without intermediaries. Official 1–2 year warranty for RTX Pro 6000 Blackwell 96GB
The RTX Pro 6000 Blackwell 96GB series by NVIDIA includes three models: Workstation Edition, Max-Q Workstation Edition and Server Edition. All models are based on the latest NVIDIA Blackwell architecture and come equipped with 96 GB of GDDR7 ECC video memory. Each modification is optimized for specific workloads, and these details define their key differences.
Each graphics card integrates 24,064 CUDA cores and supports all modern graphics and compute APIs — from DirectX 12 and Vulkan to CUDA 12.8. This makes the series suitable for visualization, deep learning, simulation, big data analysis, and generative AI. Cooling, power usage, and form factor define each model’s focus.
Specifications
- GPU Memory: 96GB GDDR7
- GPU Architecture: NVIDIA Blackwell
- NVIDIA CUDA Cores: 24,064
- 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 Outputs: 4× DisplayPort 2.1b
- Maximum Supported Displays: 4× 4096×2160 @120Hz, 4× 5120×2880 @60Hz, 2× 7680×4320 @60Hz
- Video Encoders: 4× NVENC (Gen 9), 4× NVDEC (Gen 6)
- MIG Support: up to 4× 24GB, 2× 48GB, 1× 96GB
- Power Draw: 600 W
- Power Connector: 1× PCIe CEM5 16-pin
- Cooling System: Through-flow design
- Form Factor: 5.4” H × 12” L, dual-slot, extended height
- Graphics APIs: DirectX 12, Shader Model 6.6, OpenGL 4.6, Vulkan 1.3
- Compute APIs: CUDA 12.8, OpenCL 3.0, DirectCompute
Workstation Edition: Maximum Power for Your Workstation
This version is ideal for professionals working with complex 3D scenes, CAD modeling, 8K video editing, or real-time rendering. It operates up to 2617 MHz, delivers 126 TFLOPS (FP32), and uses an active side-fan cooling system. Power consumption reaches 600 W, requiring a strong PSU but ensuring maximum performance.
Key Advantage: Uncompromised workstation-class performance.
How to Choose the Right RTX Pro 6000 Blackwell 96GB Version?
- Need the highest performance on a local workstation? Choose the Workstation Edition.
- Looking for a balance between performance and heat efficiency? Max-Q Workstation Edition is the right fit.
- Building large-scale AI or server infrastructure? Go with the Server Edition.
All three models integrate the latest NVIDIA technologies, support DisplayPort 2.1, feature GDDR7 ECC memory, and offer exceptional computational density.
Why Buy RTX Pro 6000 Blackwell 96GB from Us?
- Direct import from the USA — no intermediaries or compromises.
- 3-year warranty — reliability from day one.
- Payment options: cards, corporate VAT invoices, cryptocurrency (USDT).
- We’ll help you choose the right version for your task — from rendering to AI workloads.
Order the RTX Pro 6000 Blackwell 96GB now and get a professional-grade GPU that will elevate your projects to a new level.
Product reviews
0
50
40
30
20
10
Only logged in customers who have purchased this product may leave a review.
Product Berchmark
Overview and Analysis of the NVIDIA RTX Pro 6000 Blackwell Server Edition 96GB Graphics Card
The NVIDIA RTX Pro 6000 Blackwell Server Edition 96GB is an advanced professional graphics solution based on the latest Blackwell architecture. The graphics card is designed to meet the growing needs of data centers and server infrastructures focused on artificial intelligence tasks, deep learning, and high-performance computing (HPC). A key feature of this model is the colossal 96 GB video memory capacity, which allows working with the largest neural networks and datasets without resorting to complex memory distribution methods.
Thanks to the implementation of GDDR7 memory with ECC support and the PCIe 5.0 interface, the accelerator provides record-breaking bandwidth and data exchange speeds. The Blackwell architecture brings a significant increase in the number of CUDA cores and new-generation Tensor cores, making this card the ideal choice for generative AI tasks, cinematic-quality rendering, and complex scientific simulations. The Server Edition is optimized for continuous operation under high load conditions, offering a balance between computational power and energy efficiency.
Comparative Table of Technical Specifications
The table presents a comparison of the NVIDIA RTX Pro 6000 Blackwell Server Edition 96GB with its nine closest competitors in the series and alternative flagship solutions. The comparison includes other modifications of the Blackwell architecture, the previous Ada Lovelace generation, as well as specialized accelerators from the H100 and L40S series.
| Model | VRAM (GB) | Memory Type | Bandwidth (GB/s)* | CUDA Cores | Tensor Cores | FP16 (TFLOPS) | FP32 (TFLOPS) | FP64 (TFLOPS) | Tensor Perf (TFLOPS) | Interface | TDP (W) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| RTX Pro 6000 Blackwell Server Edition | 96 | GDDR7 ECC | 1597 | 24064 | 752 | 126 | 62.5 | 1.72 | 250 | PCIe 5.0 x16 | 400|600 |
| RTX Pro 6000 Blackwell Workstation | 96 | GDDR7 ECC | 1792 | 24064 | 752 | 110.1 | 55.1 | 1.97 | 220.2 | PCIe 5.0 x16 | 600 |
| RTX Pro 6000 Blackwell Max-Q | 96 | GDDR7 ECC | 1792 | 24064 | 752 | 110.1 | 55.1 | 1.97 | 220.2 | PCIe 5.0 x16 | 300 |
| RTX PRO 5000 Blackwell | 48 | GDDR7 | 1344 | 14080 | 440 | 73.7 | 73.7 | 1.15 | – | PCIe 5.0 x16 | 300 |
| NVIDIA RTX 6000 Ada | 48 | GDDR6 ECC | 960 | 18176 | 568 | – | 91.1 | – | 1457 | PCIe 4.0 x16 | 300 |
| NVIDIA RTX 5880 Ada | 48 | GDDR6 ECC | 960 | 14080 | 440 | – | 69.3 | – | 1108 | PCIe 4.0 x16 | 285 |
| NVIDIA L40S | 48 | GDDR6 ECC | 864 | 18176 | 568 | 733 | 366 | – | – | PCIe 4.0 x16 | 350 |
| NVIDIA H100 NVL 94GB | 94 | HBM3 | 3900 | 14592 | 432 | 1513 | 756 | 30 | 3026 | PCIe 5.0 x16 | 400 |
| NVIDIA H100 80GB | 80 | HBM2e | 2039 | 14592 | 432 | 1979 | 989 | 49 | 3958 | PCIe 5.0 x16 | 350 |
| NVIDIA A100 80GB | 80 | HBM2e | 1935 | 6912 | 432 | 312 | 156 | 9.7 | 624 | PCIe 4.0 x16 | 300 |
*Bandwidth — Memory Bandwidth. Values “-” indicate lack of data.
Analysis of the Strong Points of RTX Pro 6000 Blackwell Server Edition 96GB
Based on the presented technical data, the key competitive advantages of the graphics card can be highlighted:
- Leadership in CUDA Core Count: With 24,064 cores, the RTX Pro 6000 Blackwell Server Edition significantly outperforms both its predecessors (RTX 6000 Ada with 18,176 cores) and specialized H100 accelerators (14,592 cores). This ensures unmatched computational density for parallel data processing and rendering tasks.
- Maximum Video Memory Capacity: The presence of 96 GB of memory places this model on par with top server solutions (H100 NVL). This is double that of standard professional cards (RTX 6000 Ada, L40S), which is critical for training large language models (LLMs) and working with “heavy” scenes in 3D graphics.
- Technological Superiority of GDDR7 Memory: The use of the latest GDDR7 memory standard ensures high bandwidth (up to 1792 GB/s in the series), allowing for the efficient feeding of data to the massive number of computing cores, minimizing downtime.
- Versatility and Modern Interface: Support for PCIe 5.0 guarantees double the data exchange speed with the processor compared to Ada and Ampere generation cards (PCIe 4.0). Combined with high tensor performance, the card is a universal tool for both AI and classic graphics tasks.
Conclusion
The NVIDIA RTX Pro 6000 Blackwell Server Edition 96GB represents the most powerful solution in its class, combining record memory capacity and the advanced Blackwell architecture. Compared to competitors, it offers the best combination of computing core count and VRAM volume, making it the unrivaled choice for the most resource-intensive tasks requiring both high computational performance and the ability to work with huge data arrays in the accelerator’s RAM.
Product FAQ
This model is designed specifically for use in data centers and server infrastructure. Its main application scenarios include training large language models (LLMs), generative artificial intelligence tasks, deep learning, as well as high-performance computing (HPC) and cloud rendering.
The main difference lies in the cooling system and form factor. The Server Edition is optimized for installation in server racks and is designed to use powerful chassis fans for airflow (passive cooling). It is also tuned for continuous 24/7 operation under maximum computational loads, whereas the Workstation version is designed for desktop workstations.
The graphics card is equipped with a record-breaking 96 GB of video memory of the latest GDDR7 standard. Such capacity allows for loading and processing massive neural networks and datasets entirely, without the need for constant data exchange with system memory, which significantly speeds up operations.
Yes, the GDDR7 memory in this model supports the ECC (Error-Correcting Code) function. This is critical for professional computing, as the technology allows for the automatic detection and correction of memory bit errors, ensuring high data reliability and accuracy.
The RTX Pro 6000 Blackwell uses the high-speed PCIe 5.0 x16 interface. It provides double the bandwidth compared to the previous PCIe 4.0 standard, eliminating bottlenecks during data transfer between the processor and the graphics card. The card is also backward compatible with older slot versions.
This is a high-performance solution with high power consumption. The TDP (Thermal Design Power) of the graphics card can reach 600 W during peak load modes. Operation requires a server power supply of appropriate capacity and the presence of the necessary additional power connectors (usually 12VHPWR or adapters).
The Blackwell architecture provides a colossal performance boost due to an increased number of CUDA cores (over 24,000) and new-generation Tensor cores. This reduces the training time for AI models and accelerates rendering several times compared to solutions based on the Ada Lovelace or Ampere architectures.
When purchasing from our store, the graphics card is covered by an official manufacturer’s warranty for a period of 3 years. This confirms the reliability of the device and protects your investment in professional equipment.
Yes, the RTX Pro 6000 Blackwell Server Edition is excellent for virtualization tasks (vGPU). Thanks to the large memory volume and support for NVIDIA technologies, one card can be divided among multiple users to create powerful virtual desktops (VDI) with graphics acceleration support.
Payment & Shipping methods
Fast and reliable delivery across the European Union
Estimated transit time: 3–7 days from order confirmation. Worldwide shipping is available for customers outside the EU.
All orders are processed within 24 hours after confirmation. Tracking information is provided as soon as the parcel leaves our logistics center.
Multiple Secure Payment Methods
We accept: Visa, MasterCard, Apple Pay, Google Pay, PayPal, SEPA, iDEAL, Amazon Pay, Bancontact, International Bank Transfers, Klarna via Stripe gateway.
All transactions are encrypted and processed via certified Stripe payment gateway for your security.
Additional Notes
- Delivery times may vary depending on customs clearance and carrier schedules.
- Large or custom-built items may require additional handling time.
- Shipments are insured until delivered to the customer.
- We do not deliver to P.O. boxes or military addresses.
Customers Also Loved
(incl. VAT)
NVIDIA A100 8x40GB Baseboard (A100-8x40GB-Baseboard)
P/N: A100-8x40GB-Baseboard
45 231 € (inc. VAT (Spain))
New
New
New
New
New
NVIDIA RTX A6000 48GB (900-5G133-1700-000)
P/N: 900-5G133-1700-000
8 743 € (inc. VAT (Spain))
New
NVIDIA RTX PRO 4000 Blackwell 24GB (900-5G147-2270-000)
P/N: 900-5G147-2270-000
2 162 € (inc. VAT (Spain))
New
Reviews
There are no reviews yet.