Lenovo ThinkStation PX
Lenovo's flagship dual-Xeon tower for multi-GPU AI and simulation.
| NVIDIA GPU options | NVIDIA RTX 6000 or 2000 Ada; RTX A6000/A5500/A4500/A2000/A1000/A400; A800; T1000; T400 |
|---|---|
| Form factor | Tower |
| CPU | Intel Xeon (dual socket) |
| Storage | 512 GB – 4 TB |
Lenovo ThinkStation PX is built to order and priced per project (configuration, delivery, installation and support).
Check a model against our machines before you buy.
Pick the model and quantisation you plan to run. We'll show whether it fits in memory, how much room is left for context, and the throughput to expect. Estimates come from memory bandwidth and are replaced by our own bench figures where we have them.
Machine
Quantisation
Comfortable. 70 GB spare — room for 128k context, a second small model, or a RAG index in memory. Expect roughly 3.8 tok/s single-stream.
Machines that run this configuration
Weights 42.8 GB at 4.85 bits/param · KV cache 5.0 GB at 16k (fp16, approximate) · 10 GB reserved for OS and runtime. Speed is single-stream decode, memory-bound; prompt processing and batching behave differently. Or call an engineer on +44 7515 356 146.
Lenovo's top workstation, a dual-processor tower with room for several high-end GPUs.
Supplied and configured by Workstation: built to your chosen CPU, GPU, memory and storage, burn-in and thermal tested, imaged with your operating system and software (CUDA, PyTorch, AI Workbench or your ISV applications) and delivered ready to work. On-site installation, data migration and multi-year on-site warranty can be added. Support comes from our own UK engineers, and Trade members get free tech support on every order.
Priced on quote: tell us what you need and we will confirm price, availability and lead time.