Alternatives to Ollama
Ordered by how much they overlap with Ollama, then by score.
Alternatives, ranked
-
llama.cpp
C/C++ inference engine for LLMs on CPUs and GPUs, using the GGUF format and quantization.
Updated 48 days ago6 94.4 = Compare -
LocalAI
Self-hosted, OpenAI-compatible API that runs text, image and audio models on local hardware.
Updated 49 days ago61 86.6 = Compare -
vLLM
High-throughput LLM serving engine with paged attention and an OpenAI-compatible server.
Updated 49 days ago92 81.7 = Compare -
LM Studio
Discover, download and run local LLMs offline on Mac, Windows and Linux with an intuitive desktop interface and local OpenAI-like server.
Stale: 633 days without a release367 40.0 = Compare