VPS/VDS AI/ML

For inference APIs, retrieval-augmented generation (RAG), embedding generation and background workers.

4 vCPU | 32 GB RAM | GPU 8 GB VRAM | 200 GB NVMe

4 vCPU
32 GB RAM
GPU 8 GB VRAM
200 GB NVMe
1 Gbit/s port
3 TB of traffic

8 vCPU | 64 GB RAM | GPU 16 GB VRAM | 400 GB NVMe

8 vCPU
64 GB RAM
GPU 16 GB VRAM
400 GB NVMe
1 Gbit/s port
5 TB of traffic

16 vCPU | 128 GB RAM | GPU 24 GB VRAM | 800 GB NVMe

16 vCPU
128 GB RAM
GPU 24 GB VRAM
800 GB NVMe
1 Gbit/s port
10 TB of traffic

24 vCPU | 192 GB RAM | 2x GPU 16 GB VRAM | 1.6 TB NVMe

24 vCPU
192 GB RAM
2x GPU 16 GB VRAM
1.6 TB NVMe
1 Gbit/s port
15 TB of traffic