vLLM
High-throughput LLM serving engine.
Best for: Self-hosting at scale
Visit vLLM ↗Alternatives
O
Ollamaopen-source
Simple CLI/app to download and run open-weight LLMs locally.
94
/100
L
LM Studiofree
Desktop app to discover, download and chat with local models.
90
/100
l
llama.cppopen-source
C/C++ LLM inference engine behind much of the local AI ecosystem.
83
/100
H
Hugging Facefreemium
The hub for open models, datasets and Spaces.
75
/100