Edge0-AI/Edge0

An open-source streaming MoE inference framework — SSD expert offload + Recover-LoRA + prerouter routing prediction. Python · macOS · iOS · Android — one recipe, every device. [](https://huggingface.co/Edge0/Edge0-35B-A3B-preview) [](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) [](https://edge0.ai/discord) [](LICENSE) English | 中文 | 日本語 | Español | Français edge0 is an open-source streaming MoE inference framework. It generalizes the production-proven recipe — SSD expert offload + Recover-LoRA + prerouter routing prediction — into an extensible framework that runs large sparse-MoE models on consumer hardware: peak memory is bounded by the active expert set, not the parameter count. demand; peak memory is bounded by the active set, not the parameter count. ahead, so expert loads overlap the forward pass instead of stalling it — up to +59% decode throughput; the gain grows with storage latency, model size, and routed width K. trained by distillation from the FP teacher, recovering most of the quantization loss…