* sched: Model eviction for MLX by @jessegross in [#14569](https://github.com/ollama/ollama/pull/14569)
* mlx: add prequantized tensor packing + changes for qwen35 by @pdevine in [#14878](https://github.com/ollama/ollama/pull/14878)
* mlx: quantized embeddings, fast SwiGLU, and runtime fixes by @pdevine in [#14884](https://github.com/ollama/ollama/pull/14884)
...
Web search has been updated, and Web Fetch has been added for both cloud and local models.
When using local models with web search in OpenClaw, ensure you are signed into Ollama with ollama signin
Ollama now ships with web search and web fetch plugin for OpenClaw. This allows Ollama's models (local or cloud) to search the web for the latest content and news. This also allows OpenClaw with Ollama to be able to fetch the web and extract readable content for...
* rocm: doc driver constraints by @dhiltgen in [#14833](https://github.com/ollama/ollama/pull/14833)
* config: use native OpenClaw Ollama onboarding by @BruceMacD in [#14829](https://github.com/ollama/ollama/pull/14829)
* cmd/launch: add guards for headless mode by @ParthSareen in [#14837](https://github.com/ollama/ollama/pull/14837)
* bench: improve benchmarking tool by @dhiltgen in [#14240](https://github.com/ollama/ollama/pull/14240)
...
* rocm: doc driver constraints by @dhiltgen in [#14833](https://github.com/ollama/ollama/pull/14833)
* config: use native OpenClaw Ollama onboarding by @BruceMacD in [#14829](https://github.com/ollama/ollama/pull/14829)
* cmd/launch: add guards for headless mode by @ParthSareen in [#14837](https://github.com/ollama/ollama/pull/14837)
* bench: improve benchmarking tool by @dhiltgen in [#14240](https://github.com/ollama/ollama/pull/14240)
...
* parsers: repair unclosed arg_value tags in GLM tool calls by @BruceMacD in [#14656](https://github.com/ollama/ollama/pull/14656)
* Reapply "don't require pulling stubs for cloud models" again by @jmorganca in [#14608](https://github.com/ollama/ollama/pull/14608)
* docs: format compat docs by @mxyng in [#14678](https://github.com/ollama/ollama/pull/14678)
* create: fix localhost handling by @dhiltgen in [#14681](https://github.com/ollama/ollama/pull/14681)
...