Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier-mlx-fp16/README.md

license, base_model, pipeline_tag, library_name, tags

license	base_model	pipeline_tag	library_name	tags
apache-2.0	DavidAU/Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier	text-generation	transformers	finetune unsloth granite-4.1 reasoning thinking mlx mlx-my-repo

usermma/Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier-mlx-fp16

The Model usermma/Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier-mlx-fp16 was converted to MLX format from DavidAU/Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("usermma/Granite-4.1-30B-Claude-4.6-Opus-Thinking-Charles-Xavier-mlx-fp16")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)