Download Latest Version llama-b8671-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 / b8670
Name Modified Size InfoDownloads / Week
Parent folder
llama-b8670-xcframework.zip < 10 hours ago 175.9 MB
0
llama-b8670-bin-win-vulkan-x64.zip < 10 hours ago 56.6 MB
0
llama-b8670-bin-win-sycl-x64.zip < 10 hours ago 135.4 MB
0
llama-b8670-bin-win-opencl-adreno-arm64.zip < 10 hours ago 33.3 MB
0
llama-b8670-bin-win-hip-radeon-x64.zip < 10 hours ago 360.4 MB
0
llama-b8670-bin-win-cuda-13.1-x64.zip < 10 hours ago 168.0 MB
0
llama-b8670-bin-win-cuda-12.4-x64.zip < 10 hours ago 249.6 MB
0
llama-b8670-bin-win-cpu-x64.zip < 10 hours ago 39.4 MB
0
llama-b8670-bin-win-cpu-arm64.zip < 10 hours ago 32.2 MB
0
llama-b8670-bin-ubuntu-x64.tar.gz < 10 hours ago 31.7 MB
0
llama-b8670-bin-ubuntu-vulkan-x64.tar.gz < 10 hours ago 48.8 MB
0
llama-b8670-bin-ubuntu-vulkan-arm64.tar.gz < 10 hours ago 40.9 MB
0
llama-b8670-bin-ubuntu-s390x.tar.gz < 10 hours ago 35.0 MB
0
llama-b8670-bin-ubuntu-rocm-7.2-x64.tar.gz < 10 hours ago 167.9 MB
0
llama-b8670-bin-ubuntu-openvino-2026.0-x64.tar.gz < 10 hours ago 77.0 MB
0
llama-b8670-bin-ubuntu-arm64.tar.gz < 10 hours ago 27.8 MB
0
llama-b8670-bin-macos-x64.tar.gz < 10 hours ago 104.2 MB
0
llama-b8670-bin-macos-arm64.tar.gz < 10 hours ago 40.2 MB
0
llama-b8670-bin-910b-openEuler-x86-aclgraph.tar.gz < 10 hours ago 72.5 MB
0
llama-b8670-bin-910b-openEuler-aarch64-aclgraph.tar.gz < 10 hours ago 64.9 MB
0
llama-b8670-bin-310p-openEuler-x86.tar.gz < 10 hours ago 72.5 MB
0
llama-b8670-bin-310p-openEuler-aarch64.tar.gz < 10 hours ago 64.9 MB
0
cudart-llama-bin-win-cuda-13.1-x64.zip < 10 hours ago 402.6 MB
0
cudart-llama-bin-win-cuda-12.4-x64.zip < 10 hours ago 391.4 MB
0
b8670 source code.tar.gz < 12 hours ago 29.7 MB
0
b8670 source code.zip < 12 hours ago 30.9 MB
0
README.md < 12 hours ago 4.3 kB
0
Totals: 27 Items   3.0 GB 0
model : add HunyuanOCR support (#21395) * HunyuanOCR: add support for text and vision models - Add HunyuanOCR vision projector (perceiver-based) with Conv2d merge - Add separate HUNYUAN_OCR chat template (content-before-role format) - Handle HunyuanOCR's invalid pad_token_id=-1 in converter - Fix EOS/EOT token IDs from generation_config.json - Support xdrope RoPE scaling type - Add tensor mappings for perceiver projector (mm.before_rms, mm.after_rms, etc.) - Register HunYuanVLForConditionalGeneration for both text and mmproj conversion * fix proper mapping * Update gguf-py/gguf/tensor_mapping.py Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * Update tools/mtmd/clip.cpp Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * address comments * update * Fix typecheck * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

macOS/iOS:

Linux:

Windows:

openEuler:

Source: README.md, updated 2026-04-05