This model finding1/GLM-4.5-MLX-8.5bpw was converted to MLX format from zai-org/GLM-4.5 using mlx-lm version 0.26.3 with mlx_lm.convert --quantize --q-bits 8 --mlx-path MLX-8.5bpw --hf-path zai-org/GLM-4.5.

Downloads last month: 31

Safetensors

Model size

353B params

Tensor type

BF16

U32

F32

Model tree for finding1/GLM-4.5-MLX-8.5bpw

Base model

zai-org/GLM-4.5

Quantized

(30)

this model