Local Model Tools
Runtimes, servers, and interfaces for running language models on your own hardware instead of a hosted API.
Scoring method (open_source_ai_tools_v1): 40% GitHub activity (time-decay since last push) + 40% stars (log-normalized within category) + 20% license permissiveness, minus 5 points if archived. Last generated: 2026-07-25T05:37:31.813158+00:00
#1
10.0
Ollama
Run large language models locally
+ 176822 GitHub stars (top of category)
+ recently active
+ permissive license (MIT)
#2
9.88
llama.cpp
LLM inference in C/C++, runs on commodity hardware
+ 121522 GitHub stars (top of category)
+ recently active
+ permissive license (MIT)
#3
9.76
vLLM
High-throughput, memory-efficient inference and serving engine for LLMs
+ 87101 GitHub stars (top of category)
+ recently active
+ permissive license (Apache-2.0)
#4
9.42
SGLang
High-performance serving framework for language and multimodal models
+ 30714 GitHub stars (top of category)
+ recently active
+ permissive license (Apache-2.0)
#5
7.63
Text Generation WebUI
Open-source desktop app and web UI for running local LLMs
+ 47487 GitHub stars (top of category)
+ recently active
- restrictive/copyleft license (AGPL-3.0)
No tools match your filter.