// Run models locally
Ollamav0.40.8
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Open source Maintained Dual-use For developers
IN ONE PARAGRAPH
Ollama is get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Good for: Developers and teams who want to run models locally.
01How to start
- 1Read the official quick-start (link above).
- 2Install or sign up as the official guide describes.
- 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → sglang SGLang is a high-performance serving framework for large language models and multimodal models. ★ 38k vllm A high-throughput and memory-efficient inference and serving engine for LLMs ★ 95k llama-swap Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc ★ 5.9k gpustack A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. ★ 5.9k koboldcpp KoboldCpp - Run GGUF AI models locally with a KoboldAI UI. One File. Zero Install. ★ 12k
03Related
- ?Use Codex CLI with local or custom model providers
- ?What model size can my VRAM / RAM run?
- ?Ollama truncates long documents and the model “forgets” earlier text
- ?Where to find free LLM APIs, and what the conditions are
- ?Using LLMs compliantly in mainland China
- ?Where to start learning about LLMs: roadmap and tutorials
- ?Build a private ChatGPT on your own computer (Ollama + Open WebUI)
- ?Self-host Dify on company servers (Docker Compose)