verifier.org

LocalAI

mit, container-native, and the only one here that serves text, images and audio behind one openai-compatible endpoint.

free#self-hosting-a-drop-in-o#not-for-chatting-on-a-la

the right tool if you want infrastructure rather than an app — one mit-licensed endpoint covering more modalities than anything else here.

localai exposes an openai-compatible api spanning chat, image generation and audio, so a codebase written against openai can be pointed at it wholesale rather than per-model. gguf plus onnx and diffusers-family formats, cuda, rocm, vulkan and limited metal.

it is mit with no conditions, and docker-first, which tells you the intended audience: this is something you deploy, not something you install and click.

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

the right tool if you want infrastructure rather than an app — one mit-licensed endpoint covering more modalities than anything else here.

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-