Laskamp4 Guide

: The models use a "mixture of experts," where only a subset of the total parameters (e.g., 17 billion active parameters in the Scout model) are activated for any given task. This significantly reduces computational costs and latency while maintaining high performance.

: Designed for efficiency, this model has 17 billion active parameters. It fits on a single H100 GPU. It is optimized for high-speed performance (up to 460+ tokens per second) and long-document reasoning. Laskamp4

: This is a larger model with 400 billion parameters and 128 experts. It rivals top proprietary systems like GPT-4 and Gemini in complex reasoning, coding, and image understanding. : The models use a "mixture of experts,"