# LocalAI v3.11.0 — Release & Upgrade Intelligence
- **Product:** LocalAI (https://localai.io)
- **Version:** v3.11.0
- **Released:** Feb 07, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/localai/updates/v3.11.0/

## Executive Summary (TL;DR)
LocalAI v3.11.0. Source highlight: 🎉 LocalAI 3.11.0 Release! 🚀

## Breaking Changes & Deprecations
- | **Breaking Changes** | **ExLlama** (deprecated) and **Bark** (unmaintained) backends have been removed. |
- ⚠️ **Breaking Changes** To keep the project lean and maintainable, we have removed some older backends:
- Breaking Changes 🛠 * chore(exllama): drop backend now almost deprecated by @mudler in https://github.com/mudler/LocalAI/pull/8186 ### Bug fixes :bug:

## New Features
- **VoxCPM**: Added support for the VoxCPM backend.
- **Qwen-TTS**: Added support for Qwen-TTS models
- **Piper Voices**: Added most remaining Piper voices from Hugging Face to the gallery.
- feat(vllm-omni): add new backend
- feat(vibevoice): add ASR support
- feat: add VoxCPM tts backend

## Improvements
- **Extended Platform Support**: Major work on MLX  to improve compatibility across CUDA 12, CUDA 13, L4T (Nvidia Jetson), SBSA, and macOS Metal.

## Bug Fixes
- fix(ui): correctly display selected image model
- fix(ui): take account of reasoning in token count calculation
- fix: drop gguf VRAM estimation (now redundant)
- fix(api): Add missing field in initial OpenAI streaming response
- fix(realtime): Include noAction function in prompt template and handle tool_choice
- fix: filter GGUF and GGML files from model list