Lenovo ThinkStation PGX 4TB
Installment calculator
4,9%
interest
from 5,750,- monthly
Lenovo ThinkStation PGX 4TB
If you are interested in purchasing an AI solution or accelerator, please email us at [email protected]. We will discuss the specific solution with you and prepare a quote.
Lenovo ThinkStation PGX mini computer
Your personal AI supercomputer
The Lenovo ThinkStation PGX is a powerful mini computer designed for local AI work. In a body with a volume of approximately one litre, it offers computing power more commonly found in specialised servers. The device is built on the NVIDIA Grace Blackwell GB10 superchip, which combines a 20-core ARM architecture with 5th generation Tensor cores. With up to 1 petaflop of performance and 128GB of unified memory, it enables local training, fine-tuning and inference of large language models without the need for cloud services. The 30KL000AMK model is equipped with 4TB of M.2 NVMe PCIe 5.0 SSD storage. Suitable operating systems include NVIDIA DGX OS and Ubuntu Linux. The integrated NVIDIA ConnectX-7 SmartNIC ensures high-speed, low-latency communication. This makes the ThinkStation PGX ideal for data scientists, researchers and developers who require control over their data and computing environment.
LPDDR5x / 128GB
Operating memory
Blackwell GB10
Chip architecture
NVIDIA ConnectX
High-speed network card
NVIDIA AI Software Stack
Complete software stack
240W
Power consumptionKey features of the Lenovo ThinkStation PGX mini computer
- NVIDIA GB10 Grace Blackwell superchip with a 20-core ARM processor and Blackwell architecture GPU with 5th generation Tensor cores
- Up to 1 PFLOP performance for AI inference for local processing of the most demanding models
- 128GB of shared unified CPU and GPU memory connected by NVLink-C2C technology with 5× higher throughput than PCIe 5th generation
- Loads and runs models with up to 200 billion parameters directly in memory
- NVIDIA ConnectX-7 network card with 200Gb/s InfiniBand to connect two Lenovo ThinkStation PGX systems into a mini-cluster for working with models up to 405 billion parameters
- Encrypted 4TB M.2 NVMe storage provides ample space for large datasets, models and development projects with maximum data security
- Support for PyTorch, TensorFlow and NVIDIA NIM microservices
- Wi-Fi 7, Bluetooth 5.4, 10Gb Ethernet, 4× USB-C 4.0 (40 Gb/s) and HDMI
Data centre performance in a miniature body
At the heart of the Lenovo ThinkStation PGX is the GB10 Grace Blackwell superchip – a unique combination of a 20-core ARM processor (10× Cortex-X925 + 10× Cortex-A725) and a Blackwell architecture GPU with 5th generation Tensor cores and 4th generation RT cores. Both parts of the superchip are connected by NVLink-C2C technology, which provides 5× the throughput of PCIe 5th generation and allows the CPU and GPU to share a single 128GB pool of unified LPDDR5X memory. The result is tremendous performance that consumes a maximum of 240W and fits on any desk. This shared memory, without the traditional separation of GPU VRAM and system RAM, is the key advantage of the Lenovo ThinkStation PGX over standard desktop builds – where a GeForce RTX 5090 graphics card offers 32GB of memory, the Lenovo ThinkStation PGX provides four times that for AI models, without the need to quantise or split models across multiple devices.
A personal supercomputer that fits on any desk
The Lenovo ThinkStation PGX proves you no longer need a server room or a rack full of hardware to run the largest AI models. With its compact size, the Lenovo ThinkStation PGX fits on any desk next to your laptop. Yet it offers performance that just a few years ago required an entire server full of graphics cards. Four USB-C 4.0 ports with speeds up to 40 Gb/s, Wi-Fi 7, 10Gb Ethernet and an HDMI output ensure you can connect all your accessories without an external hub or docking station. The Lenovo ThinkStation PGX is designed for developers, scientists and AI professionals who want the full power of a local, personal AI supercomputer without relying on the cloud.
Precision cooling for maximum thermal efficiency
The Lenovo ThinkStation PGX handles even the most demanding AI tasks thanks to its sophisticated cooling solution. A pair of fans with seven-speed control ensures smooth and precise airflow according to the current load. The system thus offers 1.6× more efficient cooling than comparable compact workstations. The result is a lower operating temperature and stable maximum performance even under prolonged load.
Scalable architecture
One Lenovo ThinkStation PGX can handle models with up to 200 billion parameters. Two linked AI PCs push the boundary much further. Thanks to the integrated NVIDIA ConnectX-7 network technology, two Lenovo ThinkStation PGX systems can be combined into a single computing unit to handle models like Llama 3.1 with 405 billion parameters. The ultra-fast data throughput between nodes with minimal latency is ideal for large-scale distributed AI tasks, while hardware acceleration for TLS, IPsec and MACsec ensures encrypted transmission without burdening the processor.
Accelerate all AI tasks in a compact body
The power of the Grace Blackwell architecture in a body that fits on any desk. The Lenovo ThinkStation PGX is the ideal choice for developers, researchers and data scientists who need full-fledged AI performance without compromise. Whether you're working on large language model inference, specialising pre-trained networks or developing AI agents, the Lenovo ThinkStation PGX handles the full spectrum of AI tasks locally, quickly and without relying on cloud infrastructure.
NVIDIA AI software ecosystem and task management
The Lenovo ThinkStation PGX supports the complete NVIDIA AI software stack, which simplifies the training, management and deployment of AI tasks in a local environment. The device allows you to scale performance across your local infrastructure and integrate it into broader AI solutions without needing to rely on cloud services.
Fine-tune AI models with up to 70 billion parameters
Use the Lenovo ThinkStation PGX's 128GB of unified memory to fine-tune pre-trained models with up to 70 billion parameters right at your workplace. Training on your own data allows you to specialise AI models for specific needs, industry data or specific use cases – without sending sensitive data to the cloud or paying for expensive GPU instances. The result is a model precisely tailored to your scenario, created locally, securely and under your full control.
Lenovo ThinkStation PGX facilitates data science at the highest level
The combination of 128GB of unified memory and 1 PFLOP of parallel throughput makes the Lenovo ThinkStation PGX the ideal workstation for demanding data-analytics and machine-learning projects. Large datasets, complex computational models, and demanding training and analytical processes that previously required a powerful cloud cluster or dedicated server now run right on your desk. Fast, local and without waiting for remote infrastructure.
Inference for models with up to 200 billion parameters
5th generation Tensor cores with FP4 format support achieve performance of up to 1 PFLOP and, combined with 128GB of system memory, allow you to run inference on state-of-the-art AI models with up to 200 billion parameters right on your desktop. Test, verify and deploy models like Llama, Gemma or Qwen locally and in real time – without cloud latency, shared infrastructure, and the risk of sensitive data leaks.
Application development for robotics, industry and smart cities
The Lenovo ThinkStation PGX is an exceptional platform for developing robotic systems, smart city solutions and computer vision applications. The pre-installed NVIDIA Isaac framework for robotics, Metropolis for video analysis and Holoscan for real-time data processing enable developers to take full advantage of the performance to rapidly prototype and deploy applications – locally, without relying on cloud infrastructure, and with full support from the NVIDIA ecosystem.
Personal AI supercomputer performance
Up to 1 petaflop on inference
Up to 200 billion parameters
Local inference without cloud dependency
Connect two systems
Mini cluster for models up to 405 billion parameters
Ready to work straight away
Pre-installed NVIDIA AI software stack
Memory without compromise
128GB of unified CPU and GPU memory
Your own data
Fine-tune models with up to 70 billion parameters
Compact dimensions
150×150×51mm, 1.48kg
Secure local work
Full data control without sending to the cloudSpecifications
Use
Processor
GPU series/model
Graphics card
Hard Drive
Equipment
Colour and design
PSU
Memory
Outputs
Case
Operating system
Package contents
AI
Security and management
Product series
AI specifications
GPU configuration
Cooling system
| Code: | TI100c5d0z08 |
| Warranty: | 24 months |
| Links: | Producer's Website: |
| Manufacturer information |
Lenovo Technology B.V. organizační složka, Classic 7, Jankovcova 1603/47a, 17000 Praha 7, [email protected], https://www.lenovo.com/cz/cs/contact/; Lenovo (Slovakia) s.r.o., Landererova 12, 811 09 Bratislava, [email protected] Lenovo Technology B.V. Classic 7, Jankovcova 1603/47a, 17000 Praha 7, [email protected], https://www.lenovo.com/cz/cs/contact/; Lenovo (Slovakia) s.r.o., Landererova 12, 811 09 Bratislava, [email protected], https://www.lenovo.com/ Lenovo is the world's largest computer maker, founded in 1984. Its original name was Legend. Later it was renamed to Legend Novo ("New Legend"), abbreviated Lenovo. In 2005 it took over IBM's computer division, which was among the largest computer makers in the world. It is similarly ambitious in the field of mobile phones, where it would like to surpass Apple and Samsung. As far as this goal goes, they acquired Motorola’s mobile division in January 2014 and have been ramping up production since. The company also produces tablets, monitors, televisions, and storage solutions. Overall, they are known for delivering quality products at reasonable prices. 
|