Download Latest Version llama-b7539-bin-910b-openEuler-x86.tar.gz (48.1 MB)
Email in envelope

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

Home / b7531
Name Modified Size InfoDownloads / Week
Parent folder
llama-b7531-xcframework.zip 2025-12-24 150.5 MB
llama-b7531-bin-win-vulkan-x64.zip 2025-12-24 35.1 MB
llama-b7531-bin-win-sycl-x64.zip 2025-12-24 109.2 MB
llama-b7531-bin-win-opencl-adreno-arm64.zip 2025-12-24 16.9 MB
llama-b7531-bin-win-hip-radeon-x64.zip 2025-12-24 347.8 MB
llama-b7531-bin-win-cuda-13.1-x64.zip 2025-12-24 92.8 MB
llama-b7531-bin-win-cuda-12.4-x64.zip 2025-12-24 204.1 MB
llama-b7531-bin-win-cpu-x64.zip 2025-12-24 20.0 MB
llama-b7531-bin-win-cpu-arm64.zip 2025-12-24 16.3 MB
llama-b7531-bin-ubuntu-x64.tar.gz 2025-12-24 19.2 MB
llama-b7531-bin-ubuntu-vulkan-x64.tar.gz 2025-12-24 34.7 MB
llama-b7531-bin-ubuntu-s390x.tar.gz 2025-12-24 22.3 MB
llama-b7531-bin-macos-x64.tar.gz 2025-12-24 43.0 MB
llama-b7531-bin-macos-arm64.tar.gz 2025-12-24 16.7 MB
llama-b7531-bin-910b-openEuler-x86.tar.gz 2025-12-24 48.1 MB
llama-b7531-bin-910b-openEuler-aarch64.tar.gz 2025-12-24 43.9 MB
llama-b7531-bin-310p-openEuler-x86.tar.gz 2025-12-24 48.1 MB
llama-b7531-bin-310p-openEuler-aarch64.tar.gz 2025-12-24 43.9 MB
cudart-llama-bin-win-cuda-13.1-x64.zip 2025-12-24 402.6 MB
cudart-llama-bin-win-cuda-12.4-x64.zip 2025-12-24 391.4 MB
b7531 source code.tar.gz 2025-12-24 28.6 MB
b7531 source code.zip 2025-12-24 29.5 MB
README.md 2025-12-24 2.7 kB
Totals: 23 Items   2.2 GB 0
model : support for LlamaBidirectionalModel architecture (#18220) * model: llama-embed-nemotron * minor: python lint * changed arch-name * templated llm_build_llama to be used for both llama and llama-embed arch

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 12) - CUDA 12.4 DLLs - Windows x64 (CUDA 13) - CUDA 13.1 DLLs - Windows x64 (Vulkan) - Windows x64 (SYCL) - Windows x64 (HIP)

openEuler: - openEuler x86 (310p) - openEuler x86 (910b) - openEuler aarch64 (310p) - openEuler aarch64 (910b)

Source: README.md, updated 2025-12-24