Modelpublic

dfp-official/Laguna-S-2.1-oQ8e

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes30downloads

Model Card

Laguna-S-2.1-oQ8e

This model was quantized using oQ (oMLX v0.5.3) mixed-precision quantization.

Quantization details

—Model type: laguna
—Bits: 8
—Group size: 64
—Format: MLX safetensors