xCloud LocalAI Hosting
Run LocalAI on a managed 16 GB xCloud Cloud VPS: one OpenAI-compatible API for text, vision, voice and image models.
Overview
xCloud deploys LocalAI v4.10.0 (CPU image) on a managed Cloud VPS with 6 vCPU, 16 GB RAM and 200 GB NVMe for US$59.99 a month, which suits quantized models up to about 14B, plus gpt-oss-20b. LocalAI serves text, vision, voice and image models from its gallery through one OpenAI-compatible API (with Anthropic- and ElevenLabs-style endpoints too), using llama.cpp and whisper.cpp backends. It adds user accounts with roles and per-user API keys, and agents with tools, RAG and MCP. Free SSL and backups are included, and you can bring your own server instead, 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 2 9B, Qwen3 0.6B, Qwen3 1.7B, Qwen3 4B, Qwen3 8B, Qwen3 14B, Mistral NeMo, 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 |
| Pricing model | Monthly subscription |
| Free tier available | No |
| Data center locations | United Kingdom, United States, Netherlands, Germany |
| Hardware / GPU options | CPU-only managed Cloud VPS (no GPU): 16 GB RAM, 6 vCPU, 200 GB NVMe, 30 TB bandwidth (US$59.99/month). Or bring your own server. |
| VRAM & memory | |
| Maximum model size | 14B |
| 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.

