Alternatives to llama.cpp

Ordered by how much they overlap with llama.cpp, then by score.

Alternatives, ranked

  1. Ollama

    Runtime to download and run large language models locally, with a CLI and a REST API.

    • Higher score
    • No shared features
    Updated 2 days ago
    3 93.8 = Compare
  2. vLLM

    High-throughput LLM serving engine with paged attention and an OpenAI-compatible server.

    • No shared features
    Updated 2 days ago
    22 91.3 = Compare
  3. LocalAI

    Self-hosted, OpenAI-compatible API that runs text, image and audio models on local hardware.

    • No shared features
    Updated 2 days ago
    54 89.1 = Compare