Starstruk Logo MarkStarstruk

v0.32.15

shivangi-aneja/GaussianSpeechv0.32.15Aug 19, 2026by github-actions[bot]

AI Summary

Introduces a new desktop onboarding flow and significantly improves speed by caching model metadata, alongside bug fixes for parser errors and Qwen system messages.

Key Highlights

  • New desktop onboarding flow
  • Metadata caching cuts time-to-first-token by roughly half
  • Fixed wedge bug after stream parser error
  • Qwen 3.8 system message normalization

New Features

  • New onboarding flow
  • Metadata caching

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