Skip to content

llama.cpp

Install from the command line
$ docker pull ghcr.io/ggerganov/llama.cpp:full--b1-d359f30

Recent tagged image versions

  • full--b1-d359f30 full
    Published about 2 hours ago · Digest
    sha256:d2b752066b7ce061edf1b0307d6fdf8d6aaeb6bb3842d65f8e912756120ab08b
    2 Version downloads
  • full-cuda--b1-d359f30 full-cuda
    Published about 2 hours ago · Digest
    sha256:9a8489c53db968c02e12f45e55383cd8e73bbd3b17a4227f24d4dce7d5eb8f0f
    0 Version downloads
  • light-cuda--b1-d359f30 light-cuda
    Published about 2 hours ago · Digest
    sha256:ab900adbc1451d1b53a29dbd6f2122898fadeb9ab196e3fc165e6e9a98260e03
    0 Version downloads
  • full-d359f30921a9f62a0fd299c412ff3f270286fea6
    Published about 3 hours ago · Digest
    sha256:6c72491d26b26f18d74aca46b5c1a2288e8cca81a94a4189e056b65645100177
    0 Version downloads
  • server-rocm--b1-d359f30 server-rocm
    Published about 3 hours ago · Digest
    sha256:69afc226fe46154afa888cb572ae889e5c15adfc3ed6cbec564597c891c2f3fa
    0 Version downloads
View all tagged versions

Details

Last published

2 hours ago

Discussions

1.11K

Issues

545

Total downloads

1.89M

Collaborators 5