Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
{
"originHash" : "14c443ca8e8c4734ac842efe15d1c40af0856e85f2a4579f1ff7b75f93b2ccc7",
"pins" : [
{
"identity" : "mlx-swift",
"kind" : "remoteSourceControl",
"location" : "https://github.com/ml-explore/mlx-swift",
"state" : {
"revision" : "0bb916c67f4b9e5c682cbe02a42c701c93ab5021",
"version" : "0.31.6"
}
},
{
"identity" : "swift-argument-parser",
"kind" : "remoteSourceControl",
"location" : "https://github.com/apple/swift-argument-parser",
"state" : {
"revision" : "6a52f3251125d74daf04fcbd5e6f08a75d074382",
"version" : "1.8.2"
}
},
{
"identity" : "swift-numerics",
"kind" : "remoteSourceControl",
"location" : "https://github.com/apple/swift-numerics",
"state" : {
"revision" : "0c0290ff6b24942dadb83a929ffaaa1481df04a2",
"version" : "1.1.1"
}
}
],
"version" : 3
}