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 |
|---|---|---|
| .. | ||
| Attention | ||
| Fusions | ||
| MoE | ||
| Prefill | ||
| Primitives | ||
| Quant | ||
| Sampling | ||
| TensorCore | ||
| Vision | ||