finding1
/

GLM-4.6-MLX-8.5bpw

Text Generation

8-bit precision

Model card Files Files and versions

This model finding1/GLM-4.6-MLX-8.5bpw was converted to MLX format from zai-org/GLM-4.6 using mlx-lm version 0.28.0 plus pull request #494 with mlx_lm.convert --quantize --q-bits 8 --hf-path zai-org/GLM-4.6 --mlx-path GLM-4.6-MLX-8.5bpw.

Downloads last month: 460

Safetensors

Model size

353B params

Tensor type

BF16

·

U32

·

F32

·

Model tree for finding1/GLM-4.6-MLX-8.5bpw

Base model

zai-org/GLM-4.6

Quantized

(33)

this model