unsloth-GLM-4.5-Air-qx64-mlx

This is an experimental quant formula still under evaluation:

head, v_proj for first 4 layers set to 8 bit
v_proj for the lower layers set to 6 bit
all others set to 4 bit, quanted with group size 32

This model unsloth-GLM-4.5-Air-qx64-mlx was converted to MLX format from unsloth/GLM-4.5-Air using mlx-lm version 0.26.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("unsloth-GLM-4.5-Air-qx64-mlx")

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)