--- snapshot-1790924893+++ snapshot-1790968094@@ -2,11 +2,15 @@ 
 Release notes from ollama
 
-2026-10-02T01:05:01Z tag:github.com,2008:Repository/658928958/v0.35.1-rc2 2026-10-02T03:23:32Z
+2026-10-02T01:05:01Z tag:github.com,2008:Repository/658928958/v0.35.1 2026-10-02T18:28:37Z
 
 v0.35.1
 
-<h2>What's Changed</h2> <ul> <li>feat: allow ten web searches per response by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/ParthSareen/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/ParthSareen">@ParthSareen</a> in <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5545201138" data-permission-text="Title is private" data-url="https://github.com/ollama/ollama/issues/18602" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/18602/hovercard" href="https://github.com/ollama/ollama/pull/18602">#18602</a></li> <li>MLX: version bump by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/dhiltgen/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/dhiltgen">@dhiltgen</a> in <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5587155935" data-permission-text="Title is private" data-url="https://github.com/ollama/ollama/issues/18651" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/18651/hovercard" href="https://github.com/ollama/ollama/pull/18651">#18651</a></li> <li>llama.cpp: version bump b11232 by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/dhiltgen/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/dhiltgen">@dhiltgen</a> in <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5587469570" data-permission-text="Title is private" data-url="https://github.com/ollama/ollama/issues/18652" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/18652/hovercard" href="https://github.com/ollama/ollama/pull/18652">#18652</a></li> <li>create: support explicit model capabilities by <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="/users/dhiltgen/hovercard" data-octo-click="hovercard-link-click" data-octo-dimensions="link_type:self" href="https://github.com/dhiltgen">@dhiltgen</a> in <a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5634228710" data-permission-text="Title is private" data-url="https://github.com/ollama/ollama/issues/18708" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/18708/hovercard" href="https://github.com/ollama/ollama/pull/18708">#18708</a></li> </ul> <p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/ollama/ollama/compare/v0.35.0...v0.35.1-rc0"><tt>v0.35.0...v0.35.1-rc0</tt></a></p> github-actions[bot] tag:github.com,2008:Repository/658928958/v0.35.1-rc1 2026-10-01T22:52:04Z
+<h2>Clef decision models</h2> <p>Ollama now supports <a href="https://ollama.com/library/clef" rel="nofollow">Clef</a> and <a href="https://ollama.com/library/clef" rel="nofollow">Clef Flash</a>, Cloudflare's new open-source decision models, through <code>/v1/systemone</code>.</p> <p>Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it.</p> <div class="highlight highlight-source-shell notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="curl http://localhost:11434/v1/systemone -d '{ "model": "clef-flash", "state": "The user took this screenshot.", "images": ["<base64-encoded image>"], "questions": { "has_ollama": {"type": "noul", "instructions": "Does this image contain Ollama?"} } }'"><pre>curl http://localhost:11434/v1/systemone -d <span class="pl-s"><span class="pl-pds">'</span>{</span> <span class="pl-s"> "model": "clef-flash",</span> <span class="pl-s"> "state": "The user took this screenshot.",</span> <span class="pl-s"> "images": ["<base64-encoded image>"],</span> <span class="pl-s"> "questions": {</span> <span class="pl-s"> "has_ollama": {"type": "noul", "instructions": "Does this image contain Ollama?"}</span> <span class="pl-s"> }</span> <span class="pl-s">}<span class="pl-pds">'</span></span></pre></div> <div class="snippet-clipboard-content notranslate position-relative overflow-auto" data-snippet-clipboard-copy-content="{ "model": "clef-flash", "answers": { "has_ollama": { "type": "noul", "noul": 0.958 } }, "usage": { "input_tokens": 548, "output_tokens": 0 } }"><pre class="notranslate"><code>{ "model": "clef-flash", "answers": { "has_ollama": { "type": "noul", "noul": 0.958 } }, "usage": { "input_tokens": 548, "output_tokens": 0 } } </code></pre></div> <h2>What's Changed</h2> <ul> <li>Models using web search can now perform up to ten searches per response, up from three</li> <li>Modelfiles now support <code>CAPABILITY</code> declarations, so model creators can explicitly declare what a model can do. Declarations are preserved when creating from GGUF or safetensors, through model inheritance, and on Modelfile export</li> <li><code>ollama show</code> and the model list now report only <code>decision</code> as the capability for decision models, so clients no longer offer them for general chat, tools, or thinking</li> <li>Updated llama.cpp and the MLX engine</li> </ul> <p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/ollama/ollama/compare/v0.35.0...v0.35.1"><tt>v0.35.0...v0.35.1</tt></a></p> github-actions[bot] tag:github.com,2008:Repository/658928958/v0.35.1-rc2 2026-10-02T01:05:01Z
+
+v0.35.1-rc2
+
+<p>ci: fix missing build context (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5671220102" data-permission-text="Title is private" data-url="https://github.com/ollama/ollama/issues/18742" data-hovercard-type="pull_request" data-hovercard-url="/ollama/ollama/pull/18742/hovercard" href="https://github.com/ollama/ollama/pull/18742">#18742</a>)</p> dhiltgen tag:github.com,2008:Repository/658928958/v0.35.1-rc1 2026-10-01T22:52:04Z
 
 v0.35.1-rc1
 
@@ -38,8 +42,4 @@ 
 v0.34.4-rc1: mlxrunner: Update XGrammar to 0.2.7 for structured outputs
 
-<p>We pick up schema fixes for typed dictionary values and short arrays.</p> jessegross tag:github.com,2008:Repository/658928958/v0.34.4-rc0 2026-09-23T00:53:23Z
-
-v0.34.4-rc0: mlx: speed up Qwen 3.8 prompt processing (#18550)
-
-<ul> <li>mlx: speed up Qwen 3.8 prompt processing</li> </ul> <p>Use MLX's gated-delta kernel for long scans and fold dense MLP global scales into SwiGLU.</p> <ul> <li>address comments</li> </ul> dhiltgen+<p>We pick up schema fixes for typed dictionary values and short arrays.</p> jessegross