spicyneuron/GLM-5.3-MLX-4.5bit

zai-org/GLM-5.3-BF16 optimized for running on a Mac Studio M3 512.

• —A mixed-precision quant that balances speed, memory, and accuracy.
• —4-bit baseline with important layers at higher precision.
• —Fits into ~420 GB memory, leaving enough room for a smaller utility model.

Methodology

Quantized with a mlx-lm fork. MLX quantization options differ than llama.cpp, but the principles are the same:

• —Sensitive layers like MoE routing, attention, and output embeddings get higher precision
• —More tolerant layers like MoE experts get lower precision