LocalAI releases version 4.1.2 — new llama.cpp and Qwen3.5 model support
AI Impact Summary
LocalAI has released version 4.1.2, introducing several updates including speculative decoding settings in llama.cpp and support for the Qwen3.5 model. This release incorporates updates to underlying libraries like llama.cpp and stable-diffusion.cpp, along with documentation updates. Users should review the changes to ensure compatibility and take advantage of the new features.
Affected Systems
- Date
- 6 Apr 2026
- Change type
- capability
- Severity
- medium