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 49 days ago
    4 94.9 = Compare
  2. LocalAI

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

    • No shared features
    Updated 49 days ago
    61 86.6 = Compare
  3. vLLM

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

    • No shared features
    Updated 49 days ago
    92 81.7 = Compare
  4. LM Studio

    Discover, download and run local LLMs offline on Mac, Windows and Linux with an intuitive desktop interface and local OpenAI-like server.

    • Runs on more platforms
    • No shared features
    Stale: 633 days without a release
    367 40.0 = Compare