{"id":1517,"date":"2026-09-18T05:08:28","date_gmt":"2026-09-17T20:08:28","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/09\/18\/localai-v4-10-0-released\/"},"modified":"2026-09-18T21:42:07","modified_gmt":"2026-09-18T12:42:07","slug":"localai-v4-10-0-released","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/09\/18\/localai-v4-10-0-released\/","title":{"rendered":"LocalAI v4.10.0 Released: Fleet Dashboard &#038; M5 Support"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\">mudler\/LocalAI<\/a><\/td>\n<\/tr>\n<tr>\n<td>Version<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.10.0\">v4.10.0<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-09-18<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>MIT<\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code at collection time. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p>LocalAI version v4.10.0 has been released. LocalAI is an open-source AI engine (MIT license) written in Go that runs generative AI models such as LLMs, images, audio, and video locally on any hardware without requiring a GPU.<\/p>\n<p>This release introduces a fleet operation dashboard for monitoring and managing the state of an entire cluster, credential file management for private model sources and registries, a benchmark command for measuring performance from the CLI, and per-model environment variable settings. It also includes fixes for CVE vulnerabilities and a startup crash on Apple M5.<\/p>\n<h2>Key Changes<\/h2>\n<h3>New Features<\/h3>\n<ul>\n<li><strong>Fleet Operation Dashboard<\/strong>: The previous flat node list has been revamped into a dashboard that provides real-time visibility into cluster-wide health bands, VRAM\/RAM\/CPU\/disk capacity gauges, and replica placement of running models. It also features batched operations with concurrency limits (Drain\/Resume\/Remove) and a detailed inspector.<\/li>\n<li><strong>Credentials File for Private Sources<\/strong>: Using the <code>--credentials-file<\/code> option or the <code>LOCALAI_CREDENTIALS_FILE<\/code> environment variable, a single <code>credentials.yaml<\/code> can now centrally manage authentication for OCI registries, galleries, HTTP downloads, and GitHub repositories.<\/li>\n<li><strong>CLI Benchmark Command<\/strong>: The <code>local-ai benchmark MODEL<\/code> command has been added, allowing direct measurement of latency and throughput (completion tokens\/sec) for configured text models straight from the CLI.<\/li>\n<li><strong>Per-Model Environment Variables<\/strong>: By defining an <code>env:<\/code> map in model configuration files, environment variables such as <code>CUDA_VISIBLE_DEVICES<\/code> and <code>VLLM_CACHE_DIR<\/code> can be injected into the process on a per-model basis.<\/li>\n<li><strong>Mid-Stream System Message Control<\/strong>: Added the <code>template.system_messages_after_first<\/code> setting. To avoid errors when system messages are added mid-conversation in models like Qwen3.x, it can either merge them into the first system message (<code>\"merge\"<\/code>) or convert them into user utterances (<code>\"user\"<\/code>).<\/li>\n<li><strong>Context Size Exposure<\/strong>: The <code>\/v1\/models\/capabilities<\/code> endpoint now returns <code>ContextSize<\/code>, allowing clients to directly check the effective context window of each model.<\/li>\n<\/ul>\n<h3>Performance Improvements<\/h3>\n<ul>\n<li><strong>Load-Time LoRA Fusion in vllm-cpp<\/strong>: The vllm-cpp video backend now consumes <code>lora_adapters<\/code> and <code>lora_scales<\/code> settings to fuse LoRA deltas into DiT weights during engine loading (supported for LTX2.5 and MiniMax-H3).<\/li>\n<\/ul>\n<h3>Bug Fixes and Security<\/h3>\n<ul>\n<li><strong>Apple M5 Startup SIGSEGV Fix<\/strong>: Updated <code>go-m1cpu<\/code> to v0.2.2, fixing a segmentation fault that occurred at startup on Apple M5 hardware.<\/li>\n<li><strong>Security Vulnerability Fixes<\/strong>: Patched a total of 4 CVE vulnerabilities in <code>ip-address<\/code> (CVE-2026-69192), <code>containerd<\/code> (CVE-2026-46680, CVE-2026-53488), and <code>react-router<\/code> (GHSA-qwww-vcr4-c8h2).<\/li>\n<\/ul>\n<h2>Supported Models and Hardware<\/h2>\n<ul>\n<li><strong>New Model Galleries<\/strong>: 140 gallery entries have been added, including Qwopus 3.6, OpenResearcher, LFM2.5 DSpark, Qwen3.8 small distills \/ Flash Next, UI-Mate 27B, Homura 30B, Ornith 1.5 35B\/9B, Granite 4.2, Tiel-Coder 35B, Thomson 1.0 Small, PhoneLLM, WeMM embedding, EXL3 vllm.cpp, Gemma 4 E4B, and Orukeet for NeMo speech.<\/li>\n<li><strong>Hardware Support<\/strong>: Includes startup fixes for Apple M5 and ROCm build support for <code>stablediffusion-ggml<\/code>.<\/li>\n<\/ul>\n<h2>How to Get It<\/h2>\n<p>For detailed update instructions, please refer to the <a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.10.0\">LocalAI v4.10.0 Release Page<\/a>.<\/p>\n<p><!-- lmw:releases --><\/p>\n<h2>Releases Since Our Last Article<\/h2>\n<p><em>Compiled by Local Model Watch from the project&#8217;s GitHub releases: the versions between this release and the last one we covered, which did not get separate articles.<\/em> <em>Full history: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/engine-localai-en\/\">release tracker<\/a>.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Version<\/th>\n<th>Released<\/th>\n<th>Release notes<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>v4.9.0<\/td>\n<td>2026-08-21<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.9.0\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>v4.8.2<\/td>\n<td>2026-08-08<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.8.2\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>v4.8.1<\/td>\n<td>2026-08-07<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.8.1\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>v4.8.0<\/td>\n<td>2026-08-05<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.8.0\">GitHub<\/a><\/td>\n<\/tr>\n<tr>\n<td>v4.7.1<\/td>\n<td>2026-07-15<\/td>\n<td><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.7.1\">GitHub<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:releases --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.10.0\">https:\/\/github.com\/mudler\/LocalAI\/releases\/tag\/v4.10.0<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>LocalAI v4.10.0 is out, featuring a fleet management dashboard, Apple M5 startup crash fixes, credential file management, and new model galleries.<\/p>\n","protected":false},"author":1,"featured_media":1516,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[105],"tags":[1505,136,1507,111,592,117],"class_list":["post-1517","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-engines-and-tools","tag-apple-m5-en","tag-llm-en","tag-localai-en","tag-lora-en","tag-vllm-en","tag--en"],"lang":"en","translations":{"en":1517,"ja":1515},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/1517","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=1517"}],"version-history":[{"count":3,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/1517\/revisions"}],"predecessor-version":[{"id":1770,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/1517\/revisions\/1770"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/1516"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=1517"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=1517"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=1517"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}