0.32.4

What's Changed

• Support Laguna on Apple GPUs via the MLX engine
• Quantize draft-model output heads at the requested type when creating speculative-decoding drafts.
• Fixed Qwen3 MoE decoding for differently-quantized experts, plus faster packed gate/up projection (~4–9% on M5 Max).

Full Changelog: https://github.com/ollama/ollama/compare/v0.32.3...v0.32.4