Basher17/unsloth-granite-4.1-30b-mlx
The Model Basher17/unsloth-granite-4.1-30b-mlx was converted to MLX format from unsloth/granite-4.1-30b using mlx-lm version 0.31.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Basher17/unsloth-granite-4.1-30b-mlx")
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)
- Downloads last month
- 134
Model size
29B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized