v0.30.6

OpenMOSS/MOSS-TTSv0.30.6Jun 5, 2026by github-actions[bot]

AI Summary

This release introduces Quantization-Aware Training (QAT) optimized Gemma 4 models to significantly reduce memory requirements and enhance on-device performance. It also adds integration with the Oh My Pi AI coding agent and improves quantization capabilities for Apple Silicon.

Key Highlights

New Gemma 4 QAT models for reduced memory usage
Integration with Oh My Pi AI coding agent
MLX embedding layers use NVFP4 global scale for Apple Silicon

New Features

Gemma 4 QAT weights (e2b-it-qat, e4b-it-qat, 12b-it-qat, 26b-a4b-it-qat, 31b-it-qat)
Ollama launch omp integration with Oh My Pi

Full Release Notes

# New models
- [Gemma 4 QAT weights](https://ollama.com/library/gemma4): the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the tags ending in `-qat`:
  - `gemma4:e2b-it-qat`
  - `gemma4:e4b-it-qat`
  - `gemma4:12b-it-qat`
  - `gemma4:26b-a4b-it-qat`
  - `gemma4:31b-it-qat`


## What's Changed
* `ollama launch omp` now integrates with [Oh My Pi](https://omp.sh), an AI coding agent with IDE integration
* MLX embedding layers now use NVFP4 global scale for improved quantization on Apple Silicon


**Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.5...v0.30.6