Original model: poolside/Laguna-S-2.1
Model family: Laguna S 2.1
Model size: 118B total parameters, approximately 8B activated parameters per token
Conversion: MLX-LM conversion using the Laguna architecture implementation
Quantization: 8-bit affine attention/base weights and 4-bit affine routed experts
Quantization policy: 8-bit attention/base weights with 4-bit routed experts
Group size: 64
Published MLX package size: 63.50 GiB

Benchmarks

No comparative benchmarks are available yet. This repository does not currently provide quality, speed, memory, or benchmark comparisons against the original weights or other quantizations.

License

This is a converted and quantized derivative of the original checkpoint. It retains the upstream OpenMDW-1.1 license and applicable notices of origin.

Download MLXHub

DreamFoundries/Laguna-S-2.1-8bit-Att-4bit-Ex

Laguna-S-2.1-8bit-Att-4bit-Ex

Conversion Details

Benchmarks

License

DreamFoundries/
Laguna-S-2.1-8bit-Att-4bit-Ex