Download Latest Version llama-b9611-bin-ubuntu-openvino-2026.0-x64.tar.gz (13.8 MB)
Email in envelope

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

Home / b9606
Name Modified Size InfoDownloads / Week
Parent folder
llama-b9606-xcframework.zip < 23 hours ago 205.4 MB
llama-b9606-ui.tar.gz < 23 hours ago 2.7 MB
llama-b9606-bin-win-vulkan-x64.zip < 23 hours ago 38.4 MB
llama-b9606-bin-win-sycl-x64.zip < 23 hours ago 113.8 MB
llama-b9606-bin-win-opencl-adreno-arm64.zip < 23 hours ago 11.3 MB
llama-b9606-bin-win-hip-radeon-x64.zip < 23 hours ago 321.0 MB
llama-b9606-bin-win-cuda-13.3-x64.zip < 23 hours ago 158.9 MB
llama-b9606-bin-win-cuda-12.4-x64.zip < 23 hours ago 261.1 MB
llama-b9606-bin-win-cpu-x64.zip < 23 hours ago 16.7 MB
llama-b9606-bin-win-cpu-arm64.zip < 23 hours ago 10.7 MB
llama-b9606-bin-ubuntu-x64.tar.gz < 23 hours ago 15.4 MB
llama-b9606-bin-ubuntu-vulkan-x64.tar.gz < 23 hours ago 38.3 MB
llama-b9606-bin-ubuntu-vulkan-arm64.tar.gz < 23 hours ago 31.7 MB
llama-b9606-bin-ubuntu-sycl-fp32-x64.tar.gz < 23 hours ago 47.2 MB
llama-b9606-bin-ubuntu-sycl-fp16-x64.tar.gz < 23 hours ago 47.3 MB
llama-b9606-bin-ubuntu-s390x.tar.gz < 23 hours ago 14.2 MB
llama-b9606-bin-ubuntu-rocm-7.2-x64.tar.gz < 23 hours ago 131.1 MB
llama-b9606-bin-ubuntu-openvino-2026.0-x64.tar.gz < 23 hours ago 13.8 MB
llama-b9606-bin-ubuntu-arm64.tar.gz < 23 hours ago 12.4 MB
llama-b9606-bin-macos-x64.tar.gz < 23 hours ago 10.8 MB
llama-b9606-bin-macos-arm64.tar.gz < 23 hours ago 10.6 MB
llama-b9606-bin-android-arm64.tar.gz < 23 hours ago 75.3 MB
cudart-llama-bin-win-cuda-13.3-x64.zip < 23 hours ago 391.0 MB
cudart-llama-bin-win-cuda-12.4-x64.zip < 23 hours ago 391.4 MB
b9606 source code.tar.gz < 24 hours ago 34.8 MB
b9606 source code.zip < 24 hours ago 36.3 MB
README.md < 24 hours ago 4.7 kB
Totals: 27 Items   2.4 GB 0
spec: add EAGLE3 speculative decoding support (#18039) * llama : enable layer input extraction * spec: support eagle3 * eagle3: fix params bug * eagle3: support Gemma4 eagle3 from RedHatAI * eagle3: set sync when get features from target Co-authored-by: tnhnyzc <115956684+tnhnyzc@users.noreply.github.com> * eagle3 : fix ubatch handling in embd_layer_inp extraction and encoder Co-authored-by: Doğaç Eldenk <dogacel@gmail.com> * eagle3: adapt to upstream changes * eagle3: fix rebase issues and adapt to upstream changes * eagle3:exclude the eagle3 arch from test-llama-archs * eagle3: fix editorconfig check failures * eagle3: fix multi-seq issue in d2t vocab mapping * cont : minor style / clean-up * spec : remove `common_speculative_setup_draft_model()` * llama : clean-up unused API * eagle3: set d2t vocab mapping in decode graph * cont : assert layer inputs are configured * hparams : use n_embd_inp instead of n_embd_target_features * eagle3: make output.weight optional and inherit from target model when needed * haparams : generic norm-before-residual param * llama-ext : consistent names * cont : fix * hparams : remove target_hidden_size * cparams : rename output_layer_inp -> embeddings_layer_inp * arch : reuse ATTN_NORM_2 instead of adding new hidden norm * llama : clean-up names * cont : add assert + comment * Update conversion/llama.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: tnhnyzc <115956684+tnhnyzc@users.noreply.github.com> Co-authored-by: Doğaç Eldenk <dogacel@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

UI:

Source: README.md, updated 2026-06-12