This is an MLX checkpoint derived from
poolside/Laguna-S-2.1. It applies
REAP expert pruning to the
oQ2e-fast quantized model while retaining the original model's architecture, tokenizer, chat template, and mixed-precision quantization layout.
REAP ranks routed experts from calibration activations and removes the lowest-saliency experts independently in each sparse layer. The retained experts keep their original ordering and routing behavior.
The checkpoint includes the Laguna model implementation, tokenizer, generation configuration, and chat template required by MLX-compatible runtimes. Load the repository as an MLX model and apply the bundled chat template for conversational generation and tool-calling prompts.
This derivative follows the license and usage terms of
poolside/Laguna-S-2.1. Review the base model card for its intended uses, limitations, and license conditions.
