It's not implemented in mlx[1] yet (or llama.cpp[2]), so it may take a while. [1...

		dvt 18 days ago \| parent \| context \| favorite \| on: Accelerating Gemma 4: faster inference with multi-... It's not implemented in mlx[1] yet (or llama.cpp[2]), so it may take a while. [1] https://github.com/ml-explore/mlx-lm/pull/990 [2] https://github.com/ggml-org/llama.cpp/pull/22673