Starstruk Logo MarkStarstruk

v0.33.1

FlowiseAI/Flowisev0.33.1Aug 26, 2026by github-actions[bot]

AI Summary

This release focuses on MLX improvements, adding Flash Next support for Qwen3.8, enhancing structured output capabilities, and fixing Metal GPU timeout issues.

Key Highlights

  • MLX Qwen3.8 Flash Next support
  • Structured output support added to mlxrunner
  • Fixed Metal GPU timeouts when loading models from slow storage
  • Idempotent cmake external compat patches

New Features

  • MLX Qwen3.8 Flash Next
  • Structured output
  • GPU timeout fixes

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