LocalAI

Verified

Serves local LLM, vision, image and voice inference behind an OpenAI-compatible API, letting agents run on consumer hardware with no GPU required.

Skills

OpenAI-Compatible API
Exposes chat, embedding and audio endpoints matching the OpenAI schema so existing SDKs work unchanged.
Model Gallery
Downloads and manages models from a built-in gallery across multiple backends and quantization formats.
Multimodal Inference
Runs text, image generation, speech-to-text and text-to-speech workloads from one self-hosted service.

Infrastructure & Opslocal-inferenceopenai-compatibleself-hostedcpu-inferencemodel-gallerymultimodal-serving

Runs open-weight models locally on kernels tuned to your hardware and connects them to coding agents through the…

High-throughput LLM inference server with OpenAI-compatible API. Serves Llama, Mistral, Qwen, and 30+ model families…

Deploys models as production inference APIs with dedicated GPU deployments, Truss packaging, and OpenAI-compatible…

Serves large Mixture-of-Experts models such as DeepSeek-V4-Flash and GLM-5.2 on consumer NVIDIA GPUs, sharing work…

localai

Serves local LLM, vision, image and voice inference behind an OpenAI-compatible API, letting agents run on consumer hardware with no GPU required.

fields

nameLocalAI

providerLocalAI

urlhttps://github.com/mudler/LocalAI

categoriesinfrastructure

accessapi · cli

authnone

streamingtrue

pushfalse

verifiedtrue

officialfalse

tagslocal-inference, openai-compatible, self-hosted, cpu-inference, model-gallery, multimodal-serving

skills

openai-compatible-apiOpenAI-Compatible APIExposes chat, embedding and audio endpoints matching th…

model-managementModel GalleryDownloads and manages models from a built-in gallery ac…

multimodal-inferenceMultimodal InferenceRuns text, image generation, speech-to-text and text-to…