返回模型目录
GlobalCybersecurityAlliance /

GLM-5.3-Flash-Uncensored-MLX

HF 源站

GlobalCybersecurityAlliance/GLM-5.3-Flash-Uncensored-MLX is an uncensored open-source model hosted on Hugging Face.

Image-Text-to-TextMLX LMLicense: mitmlxquantizedlora-merged
README.md说明 / 使用方法

base_model: zai-org/GLM-5.3-Flash pipeline_tag: image-text-to-text license: mit tags:

  • mlx
  • quantized
  • lora-merged

GLM-5.3-Flash-Uncensored · MLX

Model-free MLX affine RTN exports of the LoRA-merged FP8 checkpoint.

Variants

  • 8bit/: 8-bit affine weights, group size 128.
  • 4bit/: 4-bit affine weights, group size 128.

The original block-FP8 tensors are dequantized before MLX quantization. Token embeddings and the language-model head remain in BF16. The GLM5-Next architecture must be supported by the consuming MLX runtime.

This repository inherits the MIT license of the base model.