Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Swift apple-silicongemmagemma4gemma4-26b-a4bgpgpullmllm-inferencelocal-aimacosmetalon-device-aion-device-llmswift
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| ArchInfo.swift 3.7 KB | ||
| GTurboEncoders.swift 1.8 KB | ||
| GTurboJSON.swift 7.4 KB | ||
| GTurboLayoutValidator.swift 1.6 KB | ||
| IndexLoader.swift 4.4 KB | ||
| Safetensors.swift 8.6 KB | ||
| TensorMetadata.swift 786 B | ||