Starstruk Logo MarkStarstruk

v0.33.1

ruvnet/RuViewv0.33.1Aug 26, 2026by github-actions[bot]

AI Summary

This release focuses on backend improvements for MLX and llama.cpp, adding support for Qwen3.8 Flash Next and structured outputs while fixing Metal GPU timeouts.

Key Highlights

  • MLX: Qwen3.8 Flash Next support
  • mlxrunner: Added structured output support
  • mlxrunner: Fixed Metal GPU timeouts when loading models
  • MLX and llama.cpp dependency updates

New Features

  • Structured output support in mlxrunner
  • Qwen3.8 Flash Next support

Full Release Notes

## What's Changed
* MLX: Qwen3.8 Flash Next support
* cmake: make external compat patches idempotent
* MLX and llama.cpp update
* mlxrunner: add structured output support
* mlxrunner: avoid Metal GPU timeouts when loading models from slow storage

## New Contributors
* @pd95 made their first contribution in https://github.com/ollama/ollama/pull/17948

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.33.0...v0.33.1