Downloads · 30 days
11
3% of all-time downloads
beezu/zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4
zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4 is a text generation model from beezu. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
This model beezu/zerofataGLM-4.5-Iceblink-106B-A12B-MLX-MXFP4 was converted to MLX format from zerofata/GLM-4.5-Iceblink-106B-A12B using mlx-lm version 0.28.3.
Downloads · 30 days
11
3% of all-time downloads
All-time downloads
440
Public
Parameters
107B
56.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors56.8 GB · 100%
How the weights are stored.
U32107B · 100%
From the Hugging Face model README
This model beezu/zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4 was converted to MLX format from zerofata/GLM-4.5-Iceblink-106B-A12B using mlx-lm version 0.28.3.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("beezu/zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)