Engines we build

Eighteen engines,** written from scratch. **

Most LocalAI backends wrap somebody else's engine. These were written from scratch, each one because the thing we needed was a multi-gigabyte Python install, or closed, or nobody had built it yet. What ships instead is a binary and a GGUF file, checked against the reference implementation in CI, running on the machine you already own.

Install LocalAI →How backends work

0 Engines

0 Modalities

0 Python at inference

0 Licence

All {{ len $engines }} {{ range $cats }} {{ $n := len (where $engines "category" .id) }} {{ if gt $n 0 }}{{ .label }} {{ $n }} {{ end }} {{ end }} {{ range $cats }} {{ $inCat := where $engines "category" .id }} {{ if gt (len $inCat) 0 }}

{{ .label }}

{{ .blurb }}

{{ range $inCat }} {{ $e := . }} [ {{ with $e.media }}

Video

{{ end }}

{{ $e.language }}{{ with $e.status }} {{ . }} {{ end }}

{{ $e.name }}

{{ $e.tagline }}

{{ with $e.highlights }} {{ range . }}- {{ . }} {{ end }} {{ end }} {{ with $e.clips }} {{ range . }} Video

{{ .caption }} {{ end }} {{ end }} {{ $e.name }} on GitHub ↗ ]({{%20$e.repo%20}}) {{ end }}

{{ end }} {{ end }}

Nothing in that modality yet.

The rule we hold them to

We do not ship a port until it matches the original.

Every engine here is gated against the framework it replaces, on the same input, on the same machine. That means a transcript identical to the reference, boxes that land on the same pixels, or a waveform inside a stated tolerance. Speed work comes after that, and the numbers on this page come out of each engine's own benchmark suite.

Install LocalAI →LocalAI on GitHub ↗