b9994
ggml-org/llama.cppb9994Jul 14, 2026by github-actions[bot]same day as b9993
What changed since b9993
b9994 adds Q2_0 quantization support for Metal backend.
New features
- Q2_0 quantization support for Metal backend
- Smaller model sizes on Apple Silicon
Improvements
- Optimizes memory usage and inference speed on Apple Silicon
- Enables faster inference on Apple Silicon devices
Upgrade notes
Users on macOS/iOS can now use Q2_0 quantization for smaller models. No configuration changes are required for existing setups.
Analyzed Oct 17, 2026
Upgrading?
Release notes summary
Added support for the Q2_0 quantization format on the Metal backend (macOS/iOS). This allows for smaller model sizes and faster inference on Apple Silicon devices.
Key Highlights
- Added Q2_0 quantization support for Metal backend
- Enables smaller model sizes on Apple Silicon
- Optimizes memory usage and inference speed
Release Notes (excerpt)
<details open> metal : add Q2_0 support (#25419) </details> **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) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU) **Windows:** - Windows x64 (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