The LLM Inference Directory

Quality-scored directory of 0 llm inference engines, updated daily. Every engine scored on maintenance, adoption, maturity, and community signals.

LLM inference engines for self-hosted model serving — vLLM, TGI, SGLang, Ollama, llama.cpp, and the tools that make local inference fast and efficient.

Verified

0

70–100

Established

0

50–69

Emerging

0

30–49

Experimental

0

10–29

Top engines by quality score

# Engine Score

Browse by category