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
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| Edge0Configuration8B.swift 3.5 KB | ||
| Edge0Tokenizer8B.swift 6.8 KB | ||
| ExpertTensorStore.swift 2.0 KB | ||
| GroupedExpertRouter.swift 2.2 KB | ||
| MappedFile.swift 4.1 KB | ||
| SafetensorsIndex.swift 5.5 KB | ||