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 |
|---|---|---|
| .. | ||
| DequantInt4GEMV.swift 3.5 KB | ||
| DequantInt8GEMV.swift 3.4 KB | ||
| EmbedLookupInt4.swift 2.4 KB | ||