Ollama 0.34.4
UpdateUnverifiedAdded Sep 24, 2026
- Structured outputs on thinking models now apply in a single pass, making them faster and more reliable. Fixed intermittent "model not found" errors with a large local library Fixed the macOS app becoming unresponsive when checking if ChatGPT or Codex is running. Qwen 3.8 prompt processing is faster on Apple Silicon.
Topics: LLMs, Coding agents, Performance
More Ollama releases
Every Ollama release| Date | Release | Type |
|---|---|---|
| Sep 22 | Ollama 0.34.3unverified Update | Update |
| Sep 17 | Ollama 0.34.2unverified Update | Update |
Also shipped on Sep 24, 2026
Ollama in September 2026| Date | Company | Release | Product | Type |
|---|---|---|---|---|
| Sep 24 |  Snowflake | DCM Projects capability updatesunverified | Snowflake | GA |
| Sep 24 |  Midjourney | Alpha Changelog - 9/23/26unverified | Midjourney | Preview |
| Sep 24 |  Netlify | New project activity feedunverified | Netlify | Preview |
| Sep 24 |  Retool | Retool CLIunverified | Retool | Beta |
| Sep 24 |  Buildkite | Buildkite Cache is now in public previewunverified | Buildkite | Preview |
| Sep 24 |  Vercel | Vercel Connect now supports TanStack AIunverified | Vercel platform | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.