Modelpublic

Jundot/GLM-5.3-Flash-oQ4e

sourceHugging Faceupdated 27d agoView on Hugging Face

6likes3.4kdownloads

Model Card

GLM-5.3-Flash-oQ4e

This model was quantized using oQ (oMLX v0.6.3) mixed-precision quantization.

Quantization details

—Model type: glm5_next
—Bits: 4
—Group size: 64
—Format: MLX safetensors