How to Deploy an LLM on a VPS with AI in 2026 (Step-by-Step Guide)

Quick Answer

For CPU or small GPUs: use Ollama with quantized GGUF models (Llama 3.1 8B runs on 8GB RAM). For production serving: vLLM on a dedicated GPU (RTX 4090, A100, or rented). Expose via OpenAI-compatible API behind Caddy/Traefik with HTTPS.

• Setup time: 1-3 hours
• Cost: $5/mo CPU VPS to $500/mo A100
• Throughput: 10-200 tokens/sec depending on setup

What You'll Need

• VPS with 16GB+ RAM (CPU) or GPU VPS (RunPod, Vast.ai, Hetzner GPU)
• Docker installed
• Domain + Caddy/Traefik for HTTPS
• Ollama or vLLM

Steps

1. Choose model size by hardware.

• CPU (16GB RAM): Llama 3.1 8B Q4_K_M, Qwen 2.5 7B
• Single GPU 24GB (RTX 3090/4090): Llama 3.1 70B Q4, Qwen 2.5 32B
• A100 80GB: Llama 3.1 70B full, Mixtral 8x22B Q4

1. Install Ollama (simplest). curl -fsSL https://ollama.com/install.sh | sh. Pull model: ollama pull llama3.1:8b. Ollama exposes OpenAI-compatible API on :11434.
2. Or install vLLM (production). docker run --gpus all -p 8000:8000 vllm/vllm-openai:latest --model meta-llama/Llama-3.1-8B-Instruct. Far higher throughput than Ollama.
3. Put HTTPS in front. Caddy one-liner: your-domain.com { reverse_proxy localhost:8000 }. Auto Let's Encrypt certs.
4. Add auth. Ollama/vLLM don't ship auth. Use a simple Node.js or Caddy basic-auth proxy — reject requests without Authorization: Bearer <key>.
5. Test with OpenAI SDK. new OpenAI({ baseURL: 'https://your-domain.com/v1', apiKey: 'your-key' }). Works because both expose OpenAI format.
6. Monitor. Track GPU utilization (nvidia-smi), tokens/sec, queue depth. Prometheus + Grafana on the VPS.
7. Scale. Multi-GPU with vLLM tensor parallelism. Or run multiple single-GPU nodes behind a load balancer.

Common Mistakes

• Running 70B on 16GB: OOM crashes. Check quantization fits VRAM/RAM.
• No rate limiting: One runaway client saturates the box. Add per-key limits.
• Ignoring context window: Each 1K ctx = ~500MB KV cache. Don't over-allocate.
• No HTTPS: Browsers & most OpenAI SDKs refuse HTTP. Always use Caddy/Traefik.
• Skipping quantization: Full-precision 8B needs 16GB VRAM. Q4_K_M needs 5GB with minor quality loss.

Top Tools

Tool	Best For	Price
Ollama	Easiest setup	Free
vLLM	High throughput	Free
Llama.cpp	CPU / edge	Free
Caddy	HTTPS proxy	Free
Hetzner GPU	Cheap GPU VPS	$70-500/mo

FAQs

Q: Ollama vs vLLM? Ollama: simple, slow. vLLM: complex, 10x faster at scale.

Q: Which GPU for production? RTX 4090 (24GB) for indie. A100 (80GB) for scale. H100 for frontier.

Q: Can I run on CPU only? Yes — 8B quantized model on 16GB RAM. ~5-10 tok/sec. Fine for batch jobs.

Q: Is this cheaper than OpenAI API? Above ~5M tokens/mo, yes. Below that, APIs are cheaper.

Q: Data privacy vs hosted API? 100% on-prem. Data never leaves your VPS.

Q: Can I serve multiple models? Yes — vLLM supports multi-model serving with routing.

Conclusion

Self-hosting LLMs in 2026 is easier than ever. Start with Ollama on a cheap GPU VPS, graduate to vLLM when throughput matters. Full control, full privacy, predictable cost.