Xeon 3500 AI Inference 96B Workstation Overview
This Xeon 3500 AI Inference 96B Workstation is built around the Intel Xeon W5-3535X with an RTX Pro 6000 Blackwell 96GB video card.
This combination provides a very powerful solution for development in Intel OpenVINO, Intel OneAPI, Intel openMKL, and allows for development on 96B parameter LLMs.
This is a desktop version of our Xeon 3500 AI Inference Rack Workstation.
This workstation is designed for local secured development of agentic AI swarms.
Xeon 3500 AI Inference 96B Workstation Upgrades/Changes
This generative AI workstation allows for development on 96B parameter LLMs. If you need more VRAM to hold a bigger model, we recommend AI Inference Workstations with 192GB VRAM based on Threadripper, Threadripper Pro, Xeon 2500, or Xeon 3500.
We can use other GPUs as well, please let us know if you’re interested in a different GPU.
This computer does not include a Windows license and is built to run Linux. The OS choice is up to the customer however.
Xeon 3500 AI Inference 96B Workstation Limitations
This platform is currently limited to 120 threads, 7 GPUs, and 2TB of memory. Please let us know if you need a more robust platform.
Builds In This Set
Single-Socket AI Inference Desktop Workstations (24B – 192B)
Ryzen 9 24B | Ryzen 9 32B | Ryzen 9 48B | Ryzen 9 96B
Core Ultra 9 24B | Core Ultra 9 32B | Core Ultra 9 48B | Core Ultra 9 96B
Threadripper 96B | Threadripper 192B | Threadripper Pro 96B | Threadripper Pro 192B
Xeon 2500 96B | Xeon 2500 192B | Xeon 3500 96B | Xeon 3500 192B
Single-Socket AI Training Desktop Workstations (384B)
Threadripper 384B | Threadripper Pro 384B | Xeon 3500 384B
Heavy Compute Desktop Workstations
Dual EPYC 9005 Low | Dual EPYC 9005 Medium | Dual EPYC 9005 Extreme | Dual EPYC 9005 Ultimate
