tag:github.com,2008:https://github.com/ollama/ollama/releases

Release notes from ollama

2026-05-29T14:50:36Z tag:github.com,2008:Repository/658928958/v0.30.0-rc31 2026-05-29T16:09:53Z

v0.30.0

<p>This version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon.</p> <p>While in pre-release we'd love <a href="https://github.com/ollama/ollama/pull/16031" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/16031/hovercard">feedback</a> on:</p> <ul> <li>Performance improvements or degradation</li> <li>Errors or crashes that did not previously occur</li> <li>Memory utilization improvements or degradation</li> </ul> <h2>Known issues:</h2> <ul> <li><code>laguna-xs.2</code> is not yet supported on Windows/Linux.</li> <li><code>llama3.2-vision</code> is not yet supported</li> <li><code>nomic-embed-text</code> now converts inputs to lowercase per the model card where prior Ollama versions incorrectly preserved mixed case</li> </ul> <h2>Installing:</h2> <p><strong>Mac/Linux</strong></p> <div class="snippet-clipboard-content notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.30.0-rc31 sh"><pre class="notranslate"><code>curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.30.0-rc31 sh </code></pre></div> <p><strong>Windows</strong></p> <div class="snippet-clipboard-content notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="$env:OLLAMA_VERSION="0.30.0-rc31"; irm https://ollama.com/install.ps1 | iex"><pre class="notranslate"><code>$env:OLLAMA_VERSION="0.30.0-rc31"; irm https://ollama.com/install.ps1 | iex </code></pre></div> github-actions[bot] tag:github.com,2008:Repository/658928958/v0.30.0-rc30 2026-05-29T14:32:50Z

v0.30.0-rc30

<p>version bump</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc29 2026-05-28T18:37:15Z

v0.30.0-rc29

<p>review comments</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc28 2026-05-27T16:40:36Z

v0.30.0-rc28

<p>add OLLAMA_IGPU_ENABLE and largely disable iGPUs by default</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc27 2026-05-27T00:17:48Z

v0.30.0-rc27

<p>ci: windows path workaround for CPU build</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc26 2026-05-26T23:41:33Z

v0.30.0-rc26: Merge remote-tracking branch 'upstream/main' into llama-runner-phase-0

<h1>Conflicts:</h1> <h1>server/images.go</h1> <h1>server/images_test.go</h1> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc25 2026-05-25T15:34:24Z

v0.30.0-rc25

<p>ci: fix WoA cross-compile</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc24 2026-05-24T15:46:00Z

v0.30.0-rc24

<p>version bump</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc23 2026-05-22T16:39:01Z

v0.30.0-rc23

<p>lint fix</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.30.0-rc22 2026-05-21T14:40:36Z

v0.30.0-rc22

<p>version bump</p> dhiltgen