xCloud Ollama Hosting
Run Ollama on a managed xCloud Cloud VPS with 16 or 24 GB of RAM and pull open models up to about 27B yourself.
Overview
xCloud installs Ollama in one click on a managed, CPU-only Cloud VPS, and you pull and manage open-weight models from the dashboard. Two sizes run from US$59.99 a month (6 vCPU, 16 GB RAM) to US$84.99 (8 vCPU, 24 GB RAM), which suits quantized models up to about 27B. Ollama's OpenAI-compatible API, free SSL, backups and security updates are included, with Open WebUI or LibreChat as optional chat apps. You can also bring your own server, including a GPU machine for larger models, free for one server and then US$3 to US$5 per server a month.

Specifications
| Hosting type | GPU cloud |
|---|---|
| Model families | Llama, Gemma, Qwen, Mistral, Phi, DeepSeek, gpt-oss |
| LLM models | Llama 3.2 1B Instruct, Llama 3.2 3B Instruct, Llama 3.1 8B Instruct, Gemma 3 1B, Gemma 3 4B, Gemma 3 12B, Gemma 3 27B, Gemma 2 9B, Gemma 2 27B, Qwen3 0.6B, Qwen3 1.7B, Qwen3 4B, Qwen3 8B, Qwen3 14B, Qwen3 30B-A3B, Mistral NeMo, Mistral Small 3.1, Phi-4, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Llama-8B, DeepSeek-R1-Distill-Qwen-14B, gpt-oss-20b |
| Pricing range | US$59.99 – US$84.99 |
| Pricing model | Monthly subscription |
| Free tier available | No |
| Data center locations | United States, Germany, United Kingdom, Netherlands |
| Hardware / GPU options | CPU-only managed Cloud VPS (no GPU): 16 GB RAM, 6 vCPU, 200 GB NVMe (US$59.99/month); 24 GB RAM, 8 vCPU, 300 GB NVMe (US$84.99/month). 30 TB bandwidth on each. Or bring your own server, including GPU machines. |
| VRAM & memory | |
| Maximum model size | 27B |
| OpenAI-compatible API | Yes |
News about xCloud
All news →xCloud joins LLM Hosting Pro with managed Ollama and LocalAI plans
We've added xCloud as a host, with two managed CPU plans for running open-weight models on Ollama or LocalAI. We've also added Microsoft's Phi family to the site, starting with Phi-4.

