Starstruk Logo MarkStarstruk

v0.32.15

SocAIty/SpeechCraftv0.32.15Aug 19, 2026by github-actions[bot]

AI Summary

This release adds a new desktop onboarding flow and improves caching performance, cutting time-to-first-token by approximately half. It also fixes parser errors and normalizes Qwen 3.8 system messages.

Key Highlights

  • New desktop onboarding flow on first launch
  • Caches resolved model metadata to cut TTFT by ~50%
  • Fixes bug where chat and generate wedge after parser error
  • Qwen 3.8 system messages now normalized

New Features

  • Desktop onboarding flow

Full Release Notes

## What's Changed
* New desktop onboarding flow on first launch
* Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks)
* Fixes a bug where chat and generate could wedge after a mid-stream parser error
* **Qwen 3.8** system messages are now normalized so non-leading system messages are handled consistently
* MLX and llama.cpp dependency updates

## New Contributors
* @gaugarg-nv made their first contribution in https://github.com/ollama/ollama/pull/17752

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.32.14...v0.32.15