Download Latest Version llama-b8683-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 / b8682
Name Modified Size InfoDownloads / Week
Parent folder
llama-b8682-xcframework.zip < 15 hours ago 176.0 MB
llama-b8682-bin-win-vulkan-x64.zip < 15 hours ago 56.7 MB
llama-b8682-bin-win-sycl-x64.zip < 15 hours ago 135.5 MB
llama-b8682-bin-win-opencl-adreno-arm64.zip < 15 hours ago 33.3 MB
llama-b8682-bin-win-hip-radeon-x64.zip < 15 hours ago 361.3 MB
llama-b8682-bin-win-cuda-13.1-x64.zip < 15 hours ago 168.6 MB
llama-b8682-bin-win-cuda-12.4-x64.zip < 15 hours ago 252.3 MB
llama-b8682-bin-win-cpu-x64.zip < 15 hours ago 39.4 MB
llama-b8682-bin-win-cpu-arm64.zip < 15 hours ago 32.2 MB
llama-b8682-bin-ubuntu-x64.tar.gz < 15 hours ago 31.7 MB
llama-b8682-bin-ubuntu-vulkan-x64.tar.gz < 15 hours ago 48.8 MB
llama-b8682-bin-ubuntu-vulkan-arm64.tar.gz < 15 hours ago 41.0 MB
llama-b8682-bin-ubuntu-s390x.tar.gz < 15 hours ago 34.9 MB
llama-b8682-bin-ubuntu-rocm-7.2-x64.tar.gz < 15 hours ago 168.9 MB
llama-b8682-bin-ubuntu-openvino-2026.0-x64.tar.gz < 15 hours ago 77.0 MB
llama-b8682-bin-ubuntu-arm64.tar.gz < 15 hours ago 27.9 MB
llama-b8682-bin-macos-x64.tar.gz < 15 hours ago 104.2 MB
llama-b8682-bin-macos-arm64.tar.gz < 15 hours ago 40.3 MB
llama-b8682-bin-910b-openEuler-x86-aclgraph.tar.gz < 15 hours ago 72.6 MB
llama-b8682-bin-910b-openEuler-aarch64-aclgraph.tar.gz < 15 hours ago 64.9 MB
llama-b8682-bin-310p-openEuler-x86.tar.gz < 15 hours ago 72.5 MB
llama-b8682-bin-310p-openEuler-aarch64.tar.gz < 15 hours ago 64.9 MB
cudart-llama-bin-win-cuda-13.1-x64.zip < 15 hours ago 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 15 hours ago 391.4 MB
b8682 source code.tar.gz < 17 hours ago 29.7 MB
b8682 source code.zip < 17 hours ago 30.9 MB
README.md < 17 hours ago 3.5 kB
Totals: 27 Items   3.0 GB 0
ggml: add Q1_0 1-bit quantization support (CPU) (#21273) * ggml: add Q1_0 and Q1_0_g128 1-bit quantization support (CPU) * add generic fallback for x86 * remove Q1_0 (group size 32) * rename Q1_0_g128 => Q1_0 * fix Q1_0 LlamaFileType Enum * Fix trailing spaces; add generic fallback for othre backends * Apply suggestions from code review Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * fix /r/n spacing + arch-fallback --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

macOS/iOS:

Linux:

Windows:

openEuler:

Source: README.md, updated 2026-04-06