MySoftRank
Sign in

AI tools

LLM runtimes

4 listings are ranked by release freshness and adoption until verified reviews arrive; then review quality, volume and vendor responsiveness join the score. Open any row to see its receipt. See the formula

  • 4 fresh released in the last 90 days
  • 0 aging no release for 90 to 179 days
  • 0 stale no release for 180 days or more

4 ranked listings

  1. Ollama

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

    Ollama No reviews yet Open source
    Updated 2 days ago
    1 93.8 =
    Show how this rank is calculated
    Rank receipt: Ollama
    #3 overall · #1 in category
    93.8/100
    1. Release freshness +50.0 100.0 × 50%
    2. Adoption signals +43.8 87.6 × 50%
    Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula

  2. llama.cpp

    C/C++ inference engine for LLMs on CPUs and GPUs, using the GGUF format and quantization.

    ggml.ai No reviews yet Open source
    Updated 1 day ago
    2 92.6 =
    Show how this rank is calculated
    Rank receipt: llama.cpp
    #9 overall · #2 in category
    92.6/100
    1. Release freshness +50.0 100.0 × 50%
    2. Adoption signals +42.6 85.2 × 50%
    Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula

  3. vLLM

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

    vLLM Project No reviews yet Open source
    Updated 2 days ago
    3 91.3 =
    Show how this rank is calculated
    Rank receipt: vLLM
    #22 overall · #3 in category
    91.3/100
    1. Release freshness +50.0 100.0 × 50%
    2. Adoption signals +41.4 82.7 × 50%
    Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula

  4. LocalAI

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

    LocalAI No reviews yet Open source
    Updated 2 days ago
    4 89.1 =
    Show how this rank is calculated
    Rank receipt: LocalAI
    #54 overall · #4 in category
    89.1/100
    1. Release freshness +50.0 100.0 × 50%
    2. Adoption signals +39.1 78.2 × 50%
    Data from GitHub Last sync Computed on Sponsorship weight 0%, never counted Read the full formula