LocalAI Files

Self-hosted, community-driven, local OpenAI compatible API

This is an exact mirror of the LocalAI project, hosted at https://github.com/go-skynet/LocalAI. SourceForge is not affiliated with LocalAI. For more information, see the SourceForge Open Source Mirror Directory.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
local-ai-launcher-linux.tar.xz	2025-09-18	16.2 MB	0
LocalAI-v3.5.2-checksums.txt	2025-09-18	473 Bytes	0
LocalAI-v3.5.2-source.tar.gz	2025-09-18	9.4 MB	0
local-ai-v3.5.2-darwin-amd64	2025-09-18	72.7 MB	0
local-ai-v3.5.2-darwin-arm64	2025-09-18	70.5 MB	0
local-ai-v3.5.2-linux-amd64	2025-09-18	71.3 MB	0
local-ai-v3.5.2-linux-arm64	2025-09-18	68.7 MB	0
LocalAI.dmg	2025-09-18	11.9 MB	0
README.md	2025-09-18	618 Bytes	0
v3.5.2 source code.tar.gz	2025-09-18	9.4 MB	0
v3.5.2 source code.zip	2025-09-18	9.7 MB	0
Totals: 11 Items		339.8 MB	0

What's Changed

👒 Dependencies

Revert "feat(nvidia-gpu): bump images to cuda 12.8" by @mudler in https://github.com/mudler/LocalAI/pull/6303

Other Changes

docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/6305
chore: :arrow_up: Update ggml-org/llama.cpp to 0320ac5264279d74f8ee91bafa6c90e9ab9bbb91 by @localai-bot in https://github.com/mudler/LocalAI/pull/6306

Full Changelog: https://github.com/mudler/LocalAI/compare/v3.5.1...v3.5.2

Source: README.md, updated 2025-09-18

You Might Also Like

Gen AI apps are built with MongoDB Atlas Icon

Gen AI apps are built with MongoDB Atlas

The database for AI-powered applications.

MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.

Start Free

Simple, Secure Domain Registration Icon

Simple, Secure Domain Registration

Get your domain at wholesale price. Cloudflare offers simple, secure registration with no markups, plus free DNS, CDN, and SSL integration.

Register or renew your domain and pay only what we pay. No markups, hidden fees, or surprise add-ons. Choose from over 400 TLDs (.com, .ai, .dev). Every domain is integrated with Cloudflare's industry-leading DNS, CDN, and free SSL to make your site faster and more secure. Simple, secure, at-cost domain registration.

Sign up for free

Recommended Projects

Nexa SDK
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), and speech-to-text (ASR), and text-to-speech (TTS) capabilities. Additionally, it offers an OpenAI-compatible API server with JSON schema mode for...
optillm
OptiLLM is an optimizing inference proxy for Large Language Models (LLMs) that implements state-of-the-art techniques to enhance performance and efficiency. It serves as an OpenAI API-compatible proxy, allowing for seamless integration into existing workflows while optimizing inference...
Chat4Us-Creator
Chat4Us-Creator is a lightweight open-source cross-platform chatbots creator that handle Q/A and AI-driven conversations. Escalate to human agents when needed through a messenger app. Chatbots can be created using the graphic nodes editor from basic to advanced chat flows with the ability to...
DevoxxGenie
Devoxx Genie is a fully Java-based LLM Code Assistant plugin for IntelliJ IDEA, designed to integrate with local LLM providers such as Ollama, LMStudio, GPT4All, Llama.cpp, and Exo but also cloud-based LLMs such as OpenAI, Anthropic, Mistral, Groq, Gemini, DeepInfra, DeepSeek, OpenRouter and...
LangDB AI Gateway
AI Gateway is a high-performance, open-source API gateway optimized for managing and monitoring LLM traffic at scale. Developed by the LangDB team, AI Gateway acts as an intermediary between clients and backend LLMs, providing advanced features like caching, rate limiting, prompt management, and...