Download Latest Version llama-b7271-bin-ubuntu-s390x.tar.gz (18.3 MB)
Email in envelope

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

Home / b7271
Name Modified Size InfoDownloads / Week
Parent folder
llama-b7271-xcframework.zip < 7 hours ago 146.5 MB
0
llama-b7271-xcframework.tar.gz < 7 hours ago 146.6 MB
0
llama-b7271-bin-win-vulkan-x64.zip < 7 hours ago 31.8 MB
0
llama-b7271-bin-win-sycl-x64.zip < 7 hours ago 106.1 MB
0
llama-b7271-bin-win-opencl-adreno-arm64.zip < 7 hours ago 14.0 MB
0
llama-b7271-bin-win-hip-radeon-x64.zip < 7 hours ago 343.0 MB
0
llama-b7271-bin-win-cuda-12.4-x64.zip < 7 hours ago 199.7 MB
0
llama-b7271-bin-win-cpu-x64.zip < 7 hours ago 17.0 MB
0
llama-b7271-bin-win-cpu-arm64.zip < 7 hours ago 13.5 MB
0
llama-b7271-bin-ubuntu-x64.zip < 7 hours ago 16.0 MB
0
llama-b7271-bin-ubuntu-x64.tar.gz < 7 hours ago 16.0 MB
0
llama-b7271-bin-ubuntu-vulkan-x64.zip < 7 hours ago 31.5 MB
0
llama-b7271-bin-ubuntu-vulkan-x64.tar.gz < 7 hours ago 31.5 MB
0
llama-b7271-bin-ubuntu-s390x.zip < 7 hours ago 15.8 MB
0
llama-b7271-bin-ubuntu-s390x.tar.gz < 7 hours ago 18.3 MB
0
llama-b7271-bin-macos-x64.zip < 7 hours ago 36.9 MB
0
llama-b7271-bin-macos-x64.tar.gz < 7 hours ago 37.0 MB
0
llama-b7271-bin-macos-arm64.zip < 7 hours ago 13.8 MB
0
llama-b7271-bin-macos-arm64.tar.gz < 7 hours ago 13.9 MB
0
cudart-llama-bin-win-cuda-12.4-x64.zip < 7 hours ago 391.4 MB
0
b7271 source code.tar.gz < 12 hours ago 27.8 MB
0
b7271 source code.zip < 12 hours ago 28.7 MB
0
README.md < 12 hours ago 2.1 kB
0
Totals: 23 Items   1.7 GB 0

[!WARNING] Release Format Update: Linux releases will soon use .tar.gz archives instead of .zip. Please make the necessary changes to your deployment scripts.

common : skip model validation when --help is requested (#17755) This commit skips the model validation check when the user specifies the --help option. The motivation for this is that currently and error is thrown before the --help could be processed. Now skips validation if params.usage is set, allowing help to display without requiring --model. Resolves: https://github.com/ggml-org/llama.cpp/issues/17754

macOS/iOS: - macOS Apple Silicon (arm64) - macOS Intel (x64) - iOS XCFramework

Linux: - Ubuntu x64 (CPU) - Ubuntu x64 (Vulkan) - Ubuntu s390x (CPU)

Windows: - Windows x64 (CPU) - Windows arm64 (CPU) - Windows x64 (CUDA) - Windows x64 (Vulkan) - Windows x64 (SYCL) - Windows x64 (HIP)

Source: README.md, updated 2025-12-04