Download Latest Version llama-b8641-bin-ubuntu-openvino-2026.0-x64.tar.gz (77.0 MB)
Email in envelope

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

Home / b8640
Name Modified Size InfoDownloads / Week
Parent folder
llama-b8640-xcframework.zip < 8 hours ago 175.8 MB
llama-b8640-bin-win-vulkan-x64.zip < 8 hours ago 56.3 MB
llama-b8640-bin-win-sycl-x64.zip < 8 hours ago 135.1 MB
llama-b8640-bin-win-opencl-adreno-arm64.zip < 8 hours ago 33.1 MB
llama-b8640-bin-win-hip-radeon-x64.zip < 8 hours ago 360.1 MB
llama-b8640-bin-win-cuda-13.1-x64.zip < 8 hours ago 167.7 MB
llama-b8640-bin-win-cuda-12.4-x64.zip < 8 hours ago 249.2 MB
llama-b8640-bin-win-cpu-x64.zip < 8 hours ago 39.1 MB
llama-b8640-bin-win-cpu-arm64.zip < 8 hours ago 32.0 MB
llama-b8640-bin-ubuntu-x64.tar.gz < 8 hours ago 31.6 MB
llama-b8640-bin-ubuntu-vulkan-x64.tar.gz < 8 hours ago 48.7 MB
llama-b8640-bin-ubuntu-vulkan-arm64.tar.gz < 8 hours ago 40.9 MB
llama-b8640-bin-ubuntu-s390x.tar.gz < 8 hours ago 35.3 MB
llama-b8640-bin-ubuntu-rocm-7.2-x64.tar.gz < 8 hours ago 159.2 MB
llama-b8640-bin-ubuntu-openvino-2026.0-x64.tar.gz < 8 hours ago 76.7 MB
llama-b8640-bin-ubuntu-arm64.tar.gz < 8 hours ago 27.8 MB
llama-b8640-bin-macos-x64.tar.gz < 8 hours ago 103.8 MB
llama-b8640-bin-macos-arm64.tar.gz < 8 hours ago 40.2 MB
llama-b8640-bin-910b-openEuler-x86-aclgraph.tar.gz < 8 hours ago 72.3 MB
llama-b8640-bin-910b-openEuler-aarch64-aclgraph.tar.gz < 8 hours ago 64.7 MB
llama-b8640-bin-310p-openEuler-x86.tar.gz < 8 hours ago 72.3 MB
llama-b8640-bin-310p-openEuler-aarch64.tar.gz < 8 hours ago 64.7 MB
cudart-llama-bin-win-cuda-13.1-x64.zip < 8 hours ago 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 8 hours ago 391.4 MB
b8640 source code.tar.gz < 10 hours ago 29.7 MB
b8640 source code.zip < 10 hours ago 30.9 MB
README.md < 10 hours ago 4.2 kB
Totals: 27 Items   2.9 GB 0
tests : add unit test coverage for llama_tensor_get_type (#20112) * Add unit test coverage for llama_tensor_get_type * Fix merge conflicts, add more schemas * clang formatter changes * Trailing whitespace * Update name * Start rebase * Updating files with upstream changes prior to rebase * Changes needed from rebase * Update attn_qkv schema, change throw behaviour * Fix merge conflicts * White space * Update with latest changes to state counters * Revert accidental personal CLAUDE.md changes * Change quotation mark * Reuse metadata.name since we have it * Move test-only stuff out of llama-quant.cpp * Hide the regex functionality back in llama-quant.cpp, use a unique pointer to a new struct 'compiled_tensor_type_patterns' which contains the patterns * cont : inital deslop guidelines * Cleanup based on review comments * Continue cleanup * Small cleanup * Manually set proper ordering of tensors, mostly applies to gemma * Formatting * Update tests/test-quant-type-selection.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Fix merge conflicts --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

macOS/iOS:

Linux:

Windows:

openEuler:

Source: README.md, updated 2026-04-02