Download Latest Version llama-b9480-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 / b9474
Name Modified Size InfoDownloads / Week
Parent folder
llama-b9474-xcframework.zip < 15 hours ago 199.6 MB
llama-b9474-ui.tar.gz < 15 hours ago 1.9 MB
llama-b9474-bin-win-vulkan-x64.zip < 15 hours ago 33.1 MB
llama-b9474-bin-win-opencl-adreno-arm64.zip < 15 hours ago 10.3 MB
llama-b9474-bin-win-hip-radeon-x64.zip < 15 hours ago 319.7 MB
llama-b9474-bin-win-cuda-13.3-x64.zip < 15 hours ago 158.3 MB
llama-b9474-bin-win-cuda-12.4-x64.zip < 15 hours ago 260.3 MB
llama-b9474-bin-win-cpu-x64.zip < 15 hours ago 16.1 MB
llama-b9474-bin-win-cpu-arm64.zip < 15 hours ago 9.7 MB
llama-b9474-bin-ubuntu-x64.tar.gz < 15 hours ago 14.5 MB
llama-b9474-bin-ubuntu-vulkan-x64.tar.gz < 15 hours ago 32.3 MB
llama-b9474-bin-ubuntu-vulkan-arm64.tar.gz < 15 hours ago 25.4 MB
llama-b9474-bin-ubuntu-s390x.tar.gz < 15 hours ago 13.1 MB
llama-b9474-bin-ubuntu-rocm-7.2-x64.tar.gz < 15 hours ago 130.0 MB
llama-b9474-bin-ubuntu-openvino-2026.0-x64.tar.gz < 15 hours ago 12.9 MB
llama-b9474-bin-ubuntu-arm64.tar.gz < 15 hours ago 11.6 MB
llama-b9474-bin-macos-x64.tar.gz < 15 hours ago 9.9 MB
llama-b9474-bin-macos-arm64.tar.gz < 15 hours ago 9.7 MB
llama-b9474-bin-android-arm64.tar.gz < 15 hours ago 73.7 MB
cudart-llama-bin-win-cuda-13.3-x64.zip < 15 hours ago 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 15 hours ago 391.4 MB
b9474 source code.tar.gz < 18 hours ago 34.0 MB
b9474 source code.zip < 18 hours ago 35.5 MB
README.md < 18 hours ago 4.3 kB
Totals: 24 Items   2.2 GB 0
ui: Add Thinking mode toggle with reasoning effort levels + improvements for Chat Form Add Action UI (#23434) * feat: Add "Thinking" toggle and status icon + redesign Chat Form Actions Add panel * test: Update test reference * fix: Icon * fix: E2E test command * fix: wait for greeting h1 to be visible in e2e test * fix: remove duplicate PDF option in attachment dropdown * fix: use label-based group toggle to avoid stale references * refactor: inline MCP server and tool toggles in mobile sheet * fix: serve correct build directory in e2e playwright config * feat: add reasoning effort levels selector in model dropdown * feat: Reasoning effort * refactor: Make server origin configurable via environment variable * feat: Add chat template thinking detector utility * feat: Add thinking support detection to models store * refactor: Update model selector components with thinking detection and message-specific indicators * feat: Update chat form components for model selection and thinking support * feat: Improve Reasoning controls UI * refactor: Apply suggestions from code review Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com> * fix: Model tags * refactor: Cleanup * refactor: Remove unneeded components * refactor: Cleanup

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 2026-06-02