Download Latest Version llama-b10107-bin-win-openvino-2026.2.1-x64.zip (80.4 MB)
Email in envelope

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

Home / b10105
Name Modified Size InfoDownloads / Week
Parent folder
llama-b10105-xcframework.zip 2026-07-24 259.9 MB
llama-b10105-ui.tar.gz 2026-07-24 3.1 MB
llama-b10105-bin-win-vulkan-x64.zip 2026-07-24 33.5 MB
llama-b10105-bin-win-sycl-x64.zip 2026-07-24 119.7 MB
llama-b10105-bin-win-openvino-2026.2.1-x64.zip 2026-07-24 80.4 MB
llama-b10105-bin-win-opencl-adreno-arm64.zip 2026-07-24 12.8 MB
llama-b10105-bin-win-hip-radeon-x64.zip 2026-07-24 320.9 MB
llama-b10105-bin-win-cuda-13.3-x64.zip 2026-07-24 146.3 MB
llama-b10105-bin-win-cuda-12.4-x64.zip 2026-07-24 250.2 MB
llama-b10105-bin-win-cpu-x64.zip 2026-07-24 18.2 MB
llama-b10105-bin-win-cpu-arm64.zip 2026-07-24 12.1 MB
llama-b10105-bin-ubuntu-x64.tar.gz 2026-07-24 16.3 MB
llama-b10105-bin-ubuntu-vulkan-x64.tar.gz 2026-07-24 32.2 MB
llama-b10105-bin-ubuntu-vulkan-arm64.tar.gz 2026-07-24 26.3 MB
llama-b10105-bin-ubuntu-sycl-fp32-x64.tar.gz 2026-07-24 52.6 MB
llama-b10105-bin-ubuntu-sycl-fp16-x64.tar.gz 2026-07-24 52.8 MB
llama-b10105-bin-ubuntu-s390x.tar.gz 2026-07-24 15.3 MB
llama-b10105-bin-ubuntu-rocm-7.2-x64.tar.gz 2026-07-24 125.2 MB
llama-b10105-bin-ubuntu-openvino-2026.2.1-x64.tar.gz 2026-07-24 101.6 MB
llama-b10105-bin-macos-x64.tar.gz 2026-07-24 11.1 MB
llama-b10105-bin-ubuntu-arm64.tar.gz 2026-07-24 13.2 MB
llama-b10105-bin-macos-arm64.tar.gz 2026-07-24 10.8 MB
llama-b10105-bin-android-arm64.tar.gz 2026-07-24 75.1 MB
cudart-llama-bin-win-cuda-13.3-x64.zip 2026-07-24 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip 2026-07-24 391.4 MB
b10105 source code.tar.gz 2026-07-23 36.3 MB
b10105 source code.zip 2026-07-23 38.0 MB
README.md 2026-07-23 5.6 kB
Totals: 28 Items   2.6 GB 1
args: refactor mlock/mmap/directio into load-mode (#20834) * args: overhaul mmap/mlock/dio into single arg Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: update docs with llama-gen-docs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * chore: satisfy code quality Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * args: make the `+` sign an actual modifier now Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * chore: general code clean up + comments Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: fix deprecated flags support Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: quick sanity check Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * bench: sync llama-bench argument parsing Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * fix: bugfix variable behaviour + llama-bench lm column size Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: inverse commands should do the opposite instead of doing nothing Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * bench: fix incorrect dash Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * bench: fix missing modifiers for deprecated flags Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * llama: switch back to thread_local Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: switch back to single enum Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: update arg docs Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * chore: fix missing `mlock` from llama_load_mode_from_str + cleanup llama-bench Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * llama: fix mlock not activating Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: add deprecation warning when old and new flags are combined Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * arg: cont add comment for todo in the future Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: sync with upstream Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> * docs: re-sync with upstream again Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> --------- Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

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 2026-07-23