b10153
ggml-org/llama.cppb10153Jul 27, 2026by github-actions[bot]same day as b10152
What changed since b10152
b10153 adds Nanbeige4.2 architecture support on top of b10152's MTP GPU-layer allocation fix.
New features
- Added support for the Nanbeige4.2 model architecture, allowing these models to be loaded and run.
Improvements
- Model loader extended with a new architecture path, including loop-bound checks and removal of a redundant head_dim field.
Upgrade notes
This is an additive release with no config or API changes; existing models and flags behave as before. Only users running Nanbeige4.2 models need to upgrade, and no migration is required.
Analyzed Nov 1, 2026
Upgrading?
Release notes summary
Adds support for the Nanbeige4.2 model architecture, expanding the range of supported models in the library.
Key Highlights
- New Nanbeige4.2 model support
- Cross-platform binaries for all major operating systems
Release Notes (excerpt)
<details open> model: Add support for Nanbeige4.2 (#25994) * support nanbeige4.2 model * fix * fix flake8 Lint check * fix loop bound check and drop redundant head_dim --------- Co-authored-by: root <lizongqiang@kanzhun.com> </details> **Website:** - <https://llama.app> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU)…
Published by ggml-org on GitHub.
Read the full release notesRelated Repositories
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Godot Engine – Multi-platform 2D and 3D game engine
ClickHouse® is a real-time analytics database management system
Self-hosted game stream host for Moonlight.
DuckDB is a high-performance analytical database system