Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

GLM-4.5-Air-exl3-5.5bpw

Fits into 96gb vram with 65k+ context

Safetensors

Model size

37B params

Tensor type

F16

I16

Model tree for Minthy/GLM-4.5-Air-exl3-5.5bpw

Base model

Quantized

(60)

this model