AI workstation
Data-centre capability, under a desk.
Up to 96 GB of GDDR7 per GPU and 1,792 GB/s of bandwidth put frontier-class open-weight models within reach of a single workstation — fully offline if that is what your policy requires.
- up to 96 GB
- GPU memory
- 1,792 GB/s
- Bandwidth
- 24,064
- CUDA cores
- 512-bit
- Interface
Key features
The flagship Blackwell workstation — up to 96 GB per GPU.
- 48 / 96 GB of GDDR7 memory with ECC
- 1,792 GB/s of memory bandwidth
- 24,064 CUDA cores, 512-bit memory interface
- 5th-generation Tensor Cores, 4th-generation RT Cores
Full specification
- Model
- SOIKASMRTXPROB6000
- Device type
- Multi-GPU workstation, Xeon 60-core platform
- Graphics
- 2× NVIDIA RTX PRO 6000 Blackwell
- Processor
- Intel® Xeon® w9-3595X — 60 cores / 120 threads
- Memory
- 8× 64GB DDR5-4800 2Rx4 ECC RDIMM (512GB)
- Storage
- 2× 8TB NVMe
- GPU memory
- 48 / 96 GB GDDR7 with ECC
- Memory interface
- 512-bit
- Memory bandwidth
- 1,792 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 6000
Tell us your workload and concurrency. We will confirm the configuration, lead time and the partner who delivers it in your region.