Releases · djeong20/llama.cpp

24 Jul 03:36

b5974 Latest

Latest

convert : text-only support for GLM-4.1V-9B-Thinking (#14823)

* use language_model part only, ignore visual layers

* fix rope_dim calculation

Assets 15

cudart-llama-bin-win-cuda-12.4-x64.zip

sha256:8c79a9b226de4b3cacfd1f83d24f962d0773be79f1e7b75c6af4ded7e32ae1d6

373 MB 2025-07-24T03:36:34Z
llama-b5974-bin-macos-arm64.zip

sha256:6cfcc972911f10fd30e9571b02c0b4848d06c95ec0365060604f14efcba5f86b

10.6 MB 2025-07-24T03:36:45Z
llama-b5974-bin-macos-x64.zip

sha256:5dcc2472cf81d7a7e5b4149d58d6f5b34a5d1025c7849703f59342c64b2fbb38

27.2 MB 2025-07-24T03:36:46Z
llama-b5974-bin-ubuntu-vulkan-x64.zip

sha256:47b2fe446cb4aefa26a15cebdb706d6e9a16c11a19e2f2d8858a4aab27264475

20.9 MB 2025-07-24T03:36:47Z
llama-b5974-bin-ubuntu-x64.zip

sha256:ab4bcbdaec9dd5a071caf580d8ac9b97568ab63886785b6b197efcab360a3a95

12.5 MB 2025-07-24T03:36:48Z
llama-b5974-bin-win-cpu-arm64.zip

sha256:af8d0a50edb416818a039e3d9f48c71a3f76e56ea1f35c9e778ff2f428ae58fc

10.9 MB 2025-07-24T03:36:49Z
llama-b5974-bin-win-cpu-x64.zip

sha256:7d4110ac8c207d5b8f4a321673b25b9cbdb5e8eda811864e099694df0ad0f536

13.7 MB 2025-07-24T03:36:50Z
llama-b5974-bin-win-cuda-12.4-x64.zip

sha256:08bfea2f77446078849dbc5cc240d7f3cecf642264c6e3fdc66264bc10729339

129 MB 2025-07-24T03:36:51Z
llama-b5974-bin-win-hip-radeon-x64.zip

sha256:3f6791a442eabb999cdd21e8b14147675677402990cd1c3c56665c754b869f4f

299 MB 2025-07-24T03:36:55Z
llama-b5974-bin-win-opencl-adreno-arm64.zip

sha256:4caf5b7ca57727a786977fd72c8c3928b371750194c21a04934c91461884acb4

11.2 MB 2025-07-24T03:37:02Z
Source code (zip)

2025-07-23T21:23:57Z
Source code (tar.gz)

2025-07-23T21:23:57Z

Provide feedback