verifier.org

Ollama

the easiest way in, and only partly the open-source project everyone believes it is.

free#getting-a-model-running-#which-it-still-does-bett

best onboarding in the category and a licence story that has quietly split in two — the part you type is mit, the part you click is not.

`ollama pull` and `ollama run` are why local models became approachable to people who don't build software, and the model library remains the largest and best-curated here. cuda, rocm, metal and partial vulkan, with an openai-compatible server that most local tooling assumes by default.

the licensing has drifted. the cli, engine and server are mit and remain so. the desktop gui merged into the main distribution around november 2025 without an open licence, so the interface most casual users interact with is closed. the company has also added hosted cloud models on a usage basis, which is a reasonable business and a departure from the project's origins.

the description above is ours, condensed from the ranking. pricing moves — check it on the vendor's own page before you rely on it.

pricing
free
website
github.com
our verdict

best onboarding in the category and a licence story that has quietly split in two — the part you type is mit, the part you click is not.

we researched this category against vendors' own pricing pages and licence files. that is where this line comes from — not from the vendor, and not from anything they paid for.

more local llm tools

Text Generation WebUI

oobabooga's gradio interface for running local models and loaders

#open-source#gradio

vLLM

high-throughput serving engine you can run on your own gpu

#serving#throughput

MLX LM

apple's framework for running and fine-tuning models on apple silicon

#apple-silicon

Jan

we checked thisfree

gui, server and inference engine all apache 2.0 — the only tool here where every layer is genuinely open.

#anyone-who-wants-ollama-