# LocalAI v3.2.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v3.2.0
- **Released:** Jul 24, 2025
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/localai/updates/v3.2.0/

## Executive Summary (TL;DR)
LocalAI v3.2.0. Source highlight: Welcome to LocalAI 3.2.0! This is a release that refactors our architecture to be more flexible and lightweight.

## Breaking Changes & Deprecations
- Breaking Changes 🛠 * feat: do not bundle llama-cpp anymore by @mudler in https://github.com/mudler/LocalAI/pull/5790 * feat: refactor build process, drop embedded backends by @mudler in https://github.com/mudler/LocalAI/pull/5875

## New Features
- 🧩 Modular Backends: All backends now live outside the main binary in our new Backend Gallery. This means you can update, add, or manage backends independently of LocalAI releases.
- 🗣️ Enhanced Realtime Audio: We've added speech started and stopped events for more interactive applications and OpenAI-compatible support for the input_audio field in the chat API.
- 🧠 Massive Model Gallery Expansion: Our model gallery has never been bigger! We've added over 50 new and updated models, with a focus on powerful new releases like qwen3, devstral-small, and nemotron.
- feat: do not bundle llama-cpp anymore
- feat: refactor build process, drop embedded backends
- feat(llama.cpp): allow to set kv-overrides

## Improvements
- 🗣️ Enhanced Realtime and Audio APIs: Building voice-activated applications is now easier.
- The new speech started and stopped events give you precise control over realtime audio streams.
- We now support the input_audio field in the /v1/chat/completions endpoint for multimodal audio inputs, improving OpenAI compatibility.
- ⚡️ Intel GPU Acceleration for Whisper: Our Whisper backend now supports SYCL, enabling hardware-accelerated transcriptions on Intel GPUs.

## Bug Fixes
- ✅ UI and Bug Fixes: We've squashed several bugs for a smoother experience, including a fix that correctly shows the download status for backend images in the gallery, so you always know what's happening.
- fix(gallery): automatically install model from name
- fix: Diffusers and XPU fixes
- fix(gallery): correctly show status for downloading OCI images
- fix: explorer page should not have login
- fix: dockerfile typo