This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+8 more
ReleasePort's take
Moderate signalRelease v0.23.3 fixes macOS 26 target leakage in v3 metallib for mlx image generation.
Why it matters: Patch to v0.23.3 immediately if using mlx on macOS 26 with v3 metallib.
Summary
AI summaryFixed macOS 26 target leakage in v3 metallib for mlx image generation.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Performance | Medium |
Updates imagegen runner with mlx thread affinity Updates imagegen runner with mlx thread affinity Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Bugfix | Medium |
Refines model push behavior in mlx Refines model push behavior in mlx Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Bugfix | Medium |
Hardens update flows in app Hardens update flows in app Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Bugfix | Medium |
Avoids status timeout during inference in mlx Avoids status timeout during inference in mlx Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Bugfix | Medium |
Fixes macOS 26 target leakage in v3 metallib Fixes macOS 26 target leakage in v3 metallib Source: llm_adapter@2026-05-21 Confidence: high |
— |
| Refactor | Low |
Hardens integration test suite Hardens integration test suite Source: granite4.1:30b@2026-05-23-audit Confidence: low |
— |
Full changelog
What's Changed
- mlx: refined model push behavior by @dhiltgen in https://github.com/ollama/ollama/pull/15431
- test: integration test hardening by @dhiltgen in https://github.com/ollama/ollama/pull/13532
- app: harden update flows by @dhiltgen in https://github.com/ollama/ollama/pull/16100
- mlx: update the imagegen runner for mlx thread affinity by @pdevine in https://github.com/ollama/ollama/pull/16096
- mlx: avoid status timeout during inference by @dhiltgen in https://github.com/ollama/ollama/pull/16086
- mlx: fix macOS 26 target leakage in v3 metallib by @dhiltgen in https://github.com/ollama/ollama/pull/16053
Full Changelog: https://github.com/ollama/ollama/compare/v0.23.2...v0.23.3
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About ollama
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Related context
Related tools
Beta — feedback welcome: [email protected]