v0.1.805-beta 4.45
unslothai/unslothSep 2, 2026 → Aug 31, 20260 days between releases
Generating AI comparison
Analyzing what changed between v0.1.805-beta and 4.45. This page updates automatically — usually within a minute.
The Two Releases
2x Faster Qwen3.8-Flash + GLM-5.3-Flash MTP
Sep 2, 2026· 2 months ago
This release introduces Model Training Protocol (MTP) to enable up to 2x faster inference for Qwen3.8-Flash and GLM-5.3-Flash models. It features 170+ updates across training, chat, and hardware, including new audio models, improved AMD/ROCm support, and significantly faster MLX inference on Apple Silicon.
Full release notes4.45
Aug 31, 2026· 2 months ago
A major release integrating the Rust maintenance worker and improving the admin UI with visual IAM policy editing. It enhances S3 API reliability with retry logic and adds support for Lance catalog tables and Helm chart improvements.
Full release notes