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
docs(readme): add the arXiv badge next to the model links
linyubupa5b65e6fcc66c
diff --git a/README.md b/README.mdindex 4e1ed13..5e0240a 100644--- a/README.md+++ b/README.md@@ -10,6 +10,7 @@[](https://huggingface.co/Edge0/Edge0-8B-A1B-preview)[](https://www.modelscope.cn/models/Edge0/Edge0-35B-A3B-preview)[](https://www.modelscope.cn/models/Edge0/Edge0-8B-A1B-preview)+[](https://arxiv.org/abs/2609.18063)[](https://github.com/Edge0-AI/Edge0)[](LICENSE)diff --git a/README_zh.md b/README_zh.mdindex e946e82..09f0d5e 100644--- a/README_zh.md+++ b/README_zh.md@@ -10,6 +10,7 @@[](https://huggingface.co/Edge0/Edge0-8B-A1B-preview)[](https://www.modelscope.cn/models/Edge0/Edge0-35B-A3B-preview)[](https://www.modelscope.cn/models/Edge0/Edge0-8B-A1B-preview)+[](https://arxiv.org/abs/2609.18063)[](https://github.com/Edge0-AI/Edge0)[](LICENSE)