AI workstation
Room for the whole pipeline, not just the model.
Agent workloads are rarely GPU-only — retrieval, parsing and tool execution all compete for CPU. This dual-Xeon configuration keeps them out of each other's way.
- 32 GB
- GPU memory
- 896 GB/s
- Bandwidth
- 120
- CPU cores
- 16 TB
- Storage
Key features
Dual-socket Blackwell system for concurrent agent workloads.
- 32 GB GDDR7 with ECC, 256-bit interface
- 896 GB/s of memory bandwidth
- 5th-generation Tensor Core support
- 2× NVENC (9th gen) and 2× NVDEC (6th gen) engines
Full specification
- Model
- SOIKASMRTXPROB4500
- Device type
- Dual-socket workstation, 120 CPU cores
- Graphics
- 2× NVIDIA RTX PRO 4500 Blackwell
- Processor
- 2× Intel® Xeon® w9-3595X — 120 cores / 240 threads
- Memory
- 8× 64GB DDR5-4800 2Rx4 ECC RDIMM (512GB)
- Storage
- 2× 8TB NVMe
- GPU memory
- 32 GB GDDR7 with ECC
- Memory interface
- 256-bit
- Memory bandwidth
- 896 GB/s
- Network
- 2× 10GbE RJ45 + 1× management LAN
Included with every system
Software, licensed and pre-installed
Soika Stack
GPU clustering, LLM deployment and inference management, pre-configured and licensed.
Mockingjay Network
No-code AI agent design and agent-fleet management with the Enterprise licence.
Ubuntu LTS
Hardened Linux base image with the full CUDA and container toolchain already in place.
- Parts
- 3 years
- Live service
- 3 years, engineer-led
- Support tier
- Standard 3-year; on-site service and SLA available through partners
Related
Other configurations
Sizing
Configure the SM RTX PRO 4500
Tell us your workload and concurrency. We will confirm the configuration, lead time and the partner who delivers it in your region.