Runs On My 32GB Mac
					Collection
				
Some smarter, and some MoEs
					• 
				76 items
				• 
				Updated
					
				•
					
					2
This model ERNIE-4.5-21B-A3B-Thinking-mxfp4-mlx was converted to MLX format from baidu/ERNIE-4.5-21B-A3B-Thinking using mlx-lm version 0.27.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ERNIE-4.5-21B-A3B-Thinking-mxfp4-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)
Base model
baidu/ERNIE-4.5-21B-A3B-Thinking