Download Latest Version llama-b9601-bin-ubuntu-openvino-2026.0-x64.tar.gz (13.8 MB)
Email in envelope

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

Home / b9591
Name Modified Size InfoDownloads / Week
Parent folder
llama-b9591-xcframework.zip 2026-06-10 201.8 MB
llama-b9591-ui.tar.gz 2026-06-10 2.7 MB
llama-b9591-bin-win-vulkan-x64.zip 2026-06-10 38.4 MB
llama-b9591-bin-win-opencl-adreno-arm64.zip 2026-06-10 11.3 MB
llama-b9591-bin-win-hip-radeon-x64.zip 2026-06-10 320.9 MB
llama-b9591-bin-win-cuda-13.3-x64.zip 2026-06-10 158.9 MB
llama-b9591-bin-win-cuda-12.4-x64.zip 2026-06-10 261.0 MB
llama-b9591-bin-win-cpu-x64.zip 2026-06-10 16.7 MB
llama-b9591-bin-win-cpu-arm64.zip 2026-06-10 10.7 MB
llama-b9591-bin-ubuntu-x64.tar.gz 2026-06-10 15.4 MB
llama-b9591-bin-ubuntu-vulkan-x64.tar.gz 2026-06-10 38.3 MB
llama-b9591-bin-ubuntu-vulkan-arm64.tar.gz 2026-06-10 31.7 MB
llama-b9591-bin-ubuntu-s390x.tar.gz 2026-06-10 14.1 MB
llama-b9591-bin-ubuntu-rocm-7.2-x64.tar.gz 2026-06-10 131.0 MB
llama-b9591-bin-ubuntu-openvino-2026.0-x64.tar.gz 2026-06-10 13.8 MB
llama-b9591-bin-ubuntu-arm64.tar.gz 2026-06-10 12.4 MB
llama-b9591-bin-macos-x64.tar.gz 2026-06-10 10.8 MB
llama-b9591-bin-macos-arm64.tar.gz 2026-06-10 10.5 MB
llama-b9591-bin-android-arm64.tar.gz 2026-06-10 75.1 MB
cudart-llama-bin-win-cuda-13.3-x64.zip 2026-06-10 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip 2026-06-10 391.4 MB
b9591 source code.tar.gz 2026-06-10 34.8 MB
b9591 source code.zip 2026-06-10 36.2 MB
README.md 2026-06-10 3.4 kB
Totals: 24 Items   2.2 GB 0
Remove padding and multiple D2D copies for MTP (#24086) * Make ggml_gated_delta_net take only the initial recurrent state (D, 1, n_seqs) and passes the snapshot count K as an op parameter instead of inferring it from state->ne[1]. Remove the padding hack and copy all emitted snapshots into the recurrent cache with a single strided ggml_cpy * Make GDN changes in all backends. Address review comments. * Fix CI build errors

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 2026-06-10