Download Latest Version llama-b10451-bin-win-openvino-2026.2.1-x64.zip (80.7 MB)
Email in envelope

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

Home / b10444
Name Modified Size InfoDownloads / Week
Parent folder
llama-b10444-xcframework.zip < 24 hours ago 285.2 MB
llama-b10444-ui.tar.gz < 24 hours ago 3.1 MB
llama-b10444-bin-win-vulkan-x64.zip < 24 hours ago 34.8 MB
llama-b10444-bin-win-sycl-x64.zip < 24 hours ago 119.7 MB
llama-b10444-bin-win-rocm-7.14-x64.zip < 24 hours ago 196.6 MB
llama-b10444-bin-win-openvino-2026.2.1-x64.zip < 24 hours ago 80.7 MB
llama-b10444-bin-win-opencl-adreno-arm64.zip < 24 hours ago 13.0 MB
llama-b10444-bin-win-cuda-13.4-arm64.zip < 24 hours ago 140.4 MB
llama-b10444-bin-win-cuda-13.3-x64.zip < 24 hours ago 146.7 MB
llama-b10444-bin-win-cuda-12.4-x64.zip < 24 hours ago 250.8 MB
llama-b10444-bin-win-cpu-x64.zip < 24 hours ago 18.5 MB
llama-b10444-bin-ubuntu-x64.tar.gz < 24 hours ago 16.6 MB
llama-b10444-bin-win-cpu-arm64.zip < 24 hours ago 12.3 MB
llama-b10444-bin-ubuntu-vulkan-x64.tar.gz < 24 hours ago 33.2 MB
llama-b10444-bin-ubuntu-vulkan-arm64.tar.gz < 24 hours ago 27.2 MB
llama-b10444-bin-ubuntu-sycl-fp32-x64.tar.gz < 24 hours ago 53.4 MB
llama-b10444-bin-ubuntu-sycl-fp16-x64.tar.gz < 24 hours ago 53.6 MB
llama-b10444-bin-ubuntu-s390x.tar.gz < 24 hours ago 15.5 MB
llama-b10444-bin-ubuntu-openvino-2026.2.1-x64.tar.gz < 24 hours ago 102.0 MB
llama-b10444-bin-ubuntu-arm64.tar.gz < 24 hours ago 13.5 MB
llama-b10444-bin-macos-x64.tar.gz < 24 hours ago 11.4 MB
llama-b10444-bin-macos-arm64.tar.gz < 24 hours ago 11.1 MB
llama-b10444-bin-android-arm64.tar.gz < 24 hours ago 77.8 MB
cudart-llama-bin-win-cuda-13.4-arm64.zip < 24 hours ago 153.3 MB
cudart-llama-bin-win-cuda-13.3-x64.zip < 24 hours ago 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 24 hours ago 391.4 MB
b10444 source code.tar.gz 2026-08-15 36.9 MB
b10444 source code.zip 2026-08-15 38.6 MB
README.md 2026-08-15 4.2 kB
Totals: 29 Items   2.7 GB 0
common: support --models-dir loading MTP assistant models (#24431) * common: support --models-dir loading MTP assistant models * common: preset: check for MTP models with strict prefix * common: preset: Take advantage of PR [#27005] * handle other draft types * drop eagle3 * clean up --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>

Website:

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 2026-08-15