Run LLMs locally

Runtimes and servers for running open-weight models on your own hardware — from one-command installs to high-throughput inference.

1. 1
   ollama/ollama

   Healthy signals · 174,989★ · scorecard 6.0
2. 2
   ggml-org/llama.cpp

   Healthy signals · 110,468★ · scorecard 5.4
3. 3
   vllm-project/vllm

   not yet analysed — analyse now
4. 4
   oobabooga/text-generation-webui

   not yet analysed — analyse now
5. 5
   Mozilla-Ocho/llamafile

   not yet analysed — analyse now
6. 6
   lmstudio-ai/lms

   not yet analysed — analyse now

Drawn from RepoPilot's analyzed corpus and ranked by popularity and health signals, refreshed from each repo's most-recent analysis. Informational only — not professional, security, or legal advice.