LLMKube
Kubernetes operator for LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API.
At a glance
- GitHub stars
- 252
- Last activity
- 2026-11-03
- Latest release
- v0.10.16
2026-11-02 - Commits (12 mo)
- 1.3k
- License
- Apache-2.0
- Language / platform
- Go, Docker, K8S
Maintenance health: Actively maintained — Commits in the last 3 months.
Run LLMKube yourself
- RAM: ~8 GB server (4 vCPU)
- Docker: yes
- local models need lots of RAM or a GPU; API-backed frontends need far less
Estimated monthly server cost
| Provider | Plan size | ~ USD / month | |
|---|---|---|---|
| Vultr | 8 GB | $40 | Deploy → |
| DigitalOcean | 8 GB | $48 | Deploy → |
| Akamai (Linode) | 8 GB | $48 | Deploy → |
Rough estimate from the app's stack and category, not a benchmark. Several light apps can share one server. Some hosting links may be affiliate links. We may earn a commission at no extra cost to you; it never affects which apps we list.
LLMKube is an alternative to
Similar self-hosted apps
Ollama
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
Open-WebUI
User-friendly AI Interface, supports Ollama, OpenAI API.
LobeHub
Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking.
AnythingLLM
All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
LocalAI
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).
LibreChat
Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, and plugin support.
Is this your project? Get it featured or send a correction upstream to awesome-selfhosted-data.