NVIDIA

NVIDIA RTX PRO 6000

96GB GDDR7 Blackwell-class workstation GPU — low barrier inference and AIGC

Reserved and on-demand, self-service access

£1.30/hr starting£950/mo from

Reserved and committed-use discounts up to 60%. All prices GBP, ex-VAT.

Compare NVIDIA GPUs

RTX PRO 6000 is a high-memory workstation-class NVIDIA GPU tuned for cost-efficient LLM inference, AIGC generation and small-model fine-tuning where NVLink scale-out is not required.

Memory
96GB GDDR7
1.8 TB/s bandwidth
Architecture
Ada / Blackwell
Family · NVIDIA RTX PRO
Compute (FP16)
0.38 PFLOPS (8-GPU)
BF16: 0.38 PFLOPS (8-GPU)
Interconnect
100G RoCE (no NVLink)
TDP · 600W

Highlights

  • Largest single-GPU GDDR7 memory in its class
  • Lowest entry price for NVIDIA CUDA inference
  • Drop-in for any HuggingFace model

Software stack

CUDA 12.x
PyTorch 2.x
Triton
vLLM

Best-fit scenarios

  • LLM inference (up to ~15B)
  • AIGC image / video generation
  • Small-model fine-tuning

Pricing by configuration

All available SKUs for this GPU across bare-metal, VM and container form factors. Reserved and committed-use discounts available.

On-demand starting at £1.30/h

ConfigurationGPUsVRAM totalCPUMemoryStorageNetwork£/hr£/mo
Bare Metal — 8× RTX PRO 6000
rtxpro6000-bm-8
8768GB192 vCPU1 TB DDR58× 1.92 TB NVMe800G RoCE£11.60£8,400
Virtual Machine — 1× RTX PRO 6000
Popular
rtxpro6000-vm-1
196GB30 vCPU90 GB DDR5960 GB NVMe10Gbps£1.45£1,050
Container — 1× RTX PRO 6000
rtxpro6000-ctr-1
196GB16 vCPU64 GB500 GB10Gbps£1.30£950

Prices shown are list prices in GBP (ex-VAT). Reserved capacity and committed-use discounts up to 60% available — contact sales for a custom quote.

Technova at a glance

Full-stack AI cloud

GPUs, networking, storage, managed Slurm & Kubernetes on one platform.

Manual UK deployment

Every resource deployed and configured by our UK engineering team.

UK & US data residency

UK workloads stay in Glasgow & London. US workloads in Texas. You choose the region.

Reliable

Historical uptime over 99.9% with sensible SLAs and fair compensation.

Dual-stack CUDA + ROCm

Professional full-stack expertise across both NVIDIA and AMD.

World-class support

Proactive support from ML engineers and infrastructure specialists.

Ready to deploy NVIDIA RTX PRO 6000?

Spin up a private cluster in days, or talk to our sales engineers about custom configurations.

Explore AI Cloud