GitHub repo leaderboard by stars, growth rate and activity.

• ollama

  #1ollama/ollama

  Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

  Go180,541 starslast pushed Yesterday
• vllm-project

  #2vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Python91,383 starslast pushed 23 hours ago
• sgl-project

  #3sgl-project/sglang

  SGLang is a high-performance serving framework for large language models and multimodal models.

  Python35,728 starslast pushed 23 hours ago
• StarTrail-org

  #4StarTrail-org/LEANN

  [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

  Python12,926 starslast pushed 6 days ago
• qualcomm

  #5qualcomm/GenieX

  Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

  Rust8,358 starslast pushed Yesterday
• johnbean393

  #6johnbean393/Sidekick

  A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.

  Swift3,311 starslast pushed 4 months ago
• papersgpt

  #7papersgpt/papersgpt-for-zotero

  A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.7, Claude Fable 5, Claude Opus 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.3, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.8

  JavaScript2,632 starslast pushed 3 days ago
• lightseekorg

  #8lightseekorg/tokenspeed

  TokenSpeed is a speed-of-light LLM inference engine.

  Python2,112 starslast pushed 23 hours ago

#	Repo	Language	Stars	30-day trend	Last updated
1	ollama ollama/ollama Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.	Go	180,541		last pushed Yesterday
2	vllm-project vllm-project/vllm A high-throughput and memory-efficient inference and serving engine for LLMs	Python	91,383		last pushed 23 hours ago
3	sgl-project sgl-project/sglang SGLang is a high-performance serving framework for large language models and multimodal models.	Python	35,728		last pushed 23 hours ago
4	StarTrail-org StarTrail-org/LEANN [MLsys2026 Best Paper]: https://arxiv.org/abs/2506.08276. RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.	Python	12,926		last pushed 6 days ago
5	qualcomm qualcomm/GenieX Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code	Rust	8,358		last pushed Yesterday
6	johnbean393 johnbean393/Sidekick A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.	Swift	3,311		last pushed 4 months ago
7	papersgpt papersgpt/papersgpt-for-zotero A powerful Zotero AI and MCP plugin with ChatGPT, Gemini 3.7, Claude Fable 5, Claude Opus 5, DeepSeek V4, Grok, OpenRouter, Kimi k3, GLM 5.3, SiliconFlow, GPT-oss, Gemma 4, Qwen 3.8	JavaScript	2,632		last pushed 3 days ago
8	lightseekorg lightseekorg/tokenspeed TokenSpeed is a speed-of-light LLM inference engine.	Python	2,112		last pushed 23 hours ago

All · 11,474