The llama.cpp project has released version b9882, which includes a change to use the HF_TOKEN environment variable when downloading UI assets.

  • macOS Apple Silicon (arm64) binaries are available.
  • macOS Intel (x64) binaries are provided.
  • iOS XCFramework is included in the release.
  • Ubuntu builds support CPU, Vulkan, ROCm 7.2, OpenVINO, and SYCL backends.
  • Android arm64 CPU binaries are released.
  • Windows builds cover CPU, OpenCL Adreno, CUDA 12/13, Vulkan, OpenVINO, SYCL, and HIP.
  • openEuler x86 and aarch64 builds with ACL Graph support are listed.