metadata
language:
- en
- zh
license: other
license_name: glm-4-license
pipeline_tag: text-generation
tags:
- mlx
- glm4
- moe
- prism
- abliterated
- 4bit
- quantized
- apple-silicon
library_name: mlx
base_model: Ex0bit/GLM-4.7-Flash-PRISM
GLM-4.7-Flash-PRISM — MLX 4-bit
MLX 4-bit quantized version of Ex0bit/GLM-4.7-Flash-PRISM for efficient local inference on Apple Silicon.
- Quantization: 4-bit (4.5 bits per weight, group size 64, affine mode)
- Architecture: GLM-4 MoE Lite — 47 layers, 64 routed experts, 4 active per token
- Context: 202K tokens
- Size: ~16 GB
Usage
from mlx_lm import load, generate
model, tokenizer = load("shieldstackllc/GLM-4.7-Flash-PRISM-mlx-4bit")
response = generate(model, tokenizer, prompt="Hello!", verbose=True)
Or with vMLX for native macOS inference.
About
This model is an abliterated (uncensored) variant of GLM-4.7-Flash, a Mixture-of-Experts language model by Zhipu AI / THUDM. The abliteration was done by Ex0bit as part of the PRISM series. MLX quantization by vMLX.
Also Available
- GLM-4.7-Flash-PRISM MLX 8-bit (~30 GB)
Made for vMLX
This model was converted and optimized for vMLX — a free, open source macOS native MLX inference engine for Apple Silicon. Download vMLX to run this model locally with zero configuration.
Credits
- Base model: THUDM/GLM-4 by Zhipu AI
- Abliteration: Ex0bit/GLM-4.7-Flash-PRISM
- MLX conversion: vMLX — Run AI locally on Mac. No compromises.
Contact
For questions, issues, or collaboration: admin@vmlx.net