DescriptionThis AI tool simplifies the process of running machine learning models locally, enabling developers to easily deploy and interact with various models without extensive setup. Its user-friendly interface streamlines the integration of AI into applications.
* model/parsers: suppress extra gemma4 closing tool tags by @drifkin in [#15370](https://github.com/ollama/ollama/pull/15370)
* app: update featured models by @BruceMacD in [#15373](https://github.com/ollama/ollama/pull/15373)
* launch/openclaw: patch approvedScopes baseline for TUI pairing by @ParthSareen in [#15375](https://github.com/ollama/ollama/pull/15375)
* model/parsers: add gemma4 tool call repair by @drifkin in [#15374](https://github.com/ollama/ollama/pull/15374)
* bench: add prompt calibration, context size flag, and NumCtx reporting by @dhiltgen in [#15158](https://github.com/ollama/ollama/pull/15158)
* model/parsers: fix gemma4 arg parsing when quoted strings contain " by @drifkin in [#15254](https://github.com/ollama/ollama/pull/15254)
* ggml: skip cublasGemmBatchedEx during graph reservation by @jessegross in [#15301](https://github.com/ollama/ollama/pull/15301)
...
* bench: add prompt calibration, context size flag, and NumCtx reporting by @dhiltgen in [#15158](https://github.com/ollama/ollama/pull/15158)
* model/parsers: fix gemma4 arg parsing when quoted strings contain " by @drifkin in [#15254](https://github.com/ollama/ollama/pull/15254)
* ggml: skip cublasGemmBatchedEx during graph reservation by @jessegross in [#15301](https://github.com/ollama/ollama/pull/15301)
...
Looking for a different game?
Scroll through a list of games we support