Download Latest Version llama-b9442-bin-ubuntu-openvino-2026.0-x64.tar.gz (12.9 MB)
Email in envelope

Get an email when there's a new version of llama.cpp

Home / b9437
Name Modified Size InfoDownloads / Week
Parent folder
llama-b9437-xcframework.zip < 17 hours ago 199.5 MB
llama-b9437-ui.tar.gz < 17 hours ago 1.9 MB
llama-b9437-bin-win-vulkan-x64.zip < 17 hours ago 33.1 MB
llama-b9437-bin-win-opencl-adreno-arm64.zip < 17 hours ago 10.3 MB
llama-b9437-bin-win-hip-radeon-x64.zip < 17 hours ago 319.7 MB
llama-b9437-bin-win-cuda-13.3-x64.zip < 17 hours ago 158.4 MB
llama-b9437-bin-win-cuda-12.4-x64.zip < 17 hours ago 260.2 MB
llama-b9437-bin-win-cpu-x64.zip < 17 hours ago 16.1 MB
llama-b9437-bin-win-cpu-arm64.zip < 17 hours ago 9.7 MB
llama-b9437-bin-ubuntu-x64.tar.gz < 17 hours ago 14.5 MB
llama-b9437-bin-ubuntu-vulkan-x64.tar.gz < 17 hours ago 32.2 MB
llama-b9437-bin-ubuntu-vulkan-arm64.tar.gz < 17 hours ago 25.5 MB
llama-b9437-bin-ubuntu-s390x.tar.gz < 17 hours ago 12.9 MB
llama-b9437-bin-ubuntu-rocm-7.2-x64.tar.gz < 17 hours ago 129.9 MB
llama-b9437-bin-ubuntu-openvino-2026.0-x64.tar.gz < 17 hours ago 12.9 MB
llama-b9437-bin-ubuntu-arm64.tar.gz < 17 hours ago 11.5 MB
llama-b9437-bin-macos-x64.tar.gz < 17 hours ago 9.9 MB
llama-b9437-bin-macos-arm64.tar.gz < 17 hours ago 9.7 MB
llama-b9437-bin-android-arm64.tar.gz < 17 hours ago 73.6 MB
cudart-llama-bin-win-cuda-13.3-x64.zip < 17 hours ago 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 17 hours ago 391.4 MB
b9437 source code.tar.gz < 18 hours ago 34.0 MB
b9437 source code.zip < 18 hours ago 35.4 MB
README.md < 18 hours ago 3.2 kB
Totals: 24 Items   2.2 GB 0
Support `-fa auto` in llama-bench (#23714) * Support `-fa auto` in llama-bench Make the default value of `-ngl` -1, similar to other tools. Update README with latest usage and examples * Address review comments

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

Source: README.md, updated 2026-05-30