WASTE Open-Sourced, Kimi K3 Runs on 64GB MacBook

SQLite AI, an edge database company, has open-sourced its inference engine WASTE, allowing the full Kimi K3 to run on a 64GB MacBook Pro. The converted model is approximately 1TB in size, with a speed of 0.49 to 0.54 tokens per second. WASTE retains about 27GB of the model backbone in memory, with over 80,000 experts stored on the built-in SSD, reading only the currently called expert from the hard drive for each generated token. This version has not undergone distillation, pruning, or expert removal, but the expert weights have been re-quantized to 3-bit, while the model backbone uses 4-bit and 8-bit.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.