Change8

v0.23.1-rc0

📦 ollamaView on GitHub →
1 features🐛 1 fixes🔧 2 symbols

Summary

This release introduces Gemma 4 MTP speculative decoding support for Macs, significantly boosting performance for the Gemma 4 31B model on coding tasks, alongside underlying threading fixes and a Go version bump.

Migration Steps

  1. To use the new MTP speculative decoding for Gemma 4 31B, run: ollama run gemma4:31b-coding-mtp-bf16

✨ New Features

  • Gemma 4 MTP (Multi-token Processing) speculative decoding is now supported on Macs, potentially offering over a 2x speed increase for the Gemma 4 31B model on coding tasks.

🐛 Bug Fixes

  • Threading fixes applied to MLX and MLX-C.

Affected Symbols