Open-Source WASTE Engine Runs Trillion-Parameter Kimi K3 on Laptops
A new open-source C engine named WASTE allows consumer laptops to run the massive 2.78-trillion-parameter Kimi K3 model. Utilizing only 29GB of memory, this weight-aware streaming tensor engine achieves around 0.5 tokens per second, drastically lowering the hardware barrier for deploying massive AI models.
2026-08-01 ~ 2026-08-01 · 3 related posts
- Full 2.78T-parameter Kimi K3 Runs on Consumer Laptop via NVMe Streaming — rickasaurus · 2026-08-01
- Open-Source Engine 'Waste' Runs Kimi K3 on Just 29GB of RAM — galapag0 · 2026-08-01
- Run 2.78T-Parameter Kimi K3 on a Laptop: WASTE Engine Achieves 0.5 TPS — zainhas · 2026-08-01