v0.32.10

Breaking Changes

📅 Aug 12, 2026📦 ollamaView on GitHub →

⚠ 1 breaking✨ 1 features🐛 1 fixes

Summary

This release adjusts the default repeat penalty for models to 1.0, improving speculative decoding speed, and introduces faster prefill performance for certain MLX models. A bug in blob verification has also been fixed.

⚠️ Breaking Changes

Models that previously defaulted to a `repeat_penalty` of 1.1 will now default to 1.0 (off). To maintain the previous behavior for older models, explicitly set the `repeat_penalty` parameter for those models.

✨ New Features

Faster prefill on NVFP4 MLX models with a global scale, resulting in approximately 7-8% speedup on Qwen3.6 and Muse Glimmer.

🐛 Bug Fixes

Blob verification is no longer skipped when an OCI manifest's config and layer share the same digest.