60 upvotes
Tideway enables MoE inference on consumer PCs
What is Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices?
Tideway adds a phase-aware tiered memory manager that streams parts of a mixture-of-experts model between RAM, GPU memory and disk during inference. This makes it possible to run large MoE models locally on a typical laptop.
Who it is for
Developers who need private, low-cost AI agents can now run big MoE models on-device instead of calling expensive APIs.
The story so far
Early Signal first spotted Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices on November 19, 2026, with 60 upvotes. Early Signal files it under LLMs, Inference, Agents.