How to use from the
Use from the
MLX library
# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("LetheanNetwork/lemrd-mlx-bf16")
config = load_config("LetheanNetwork/lemrd-mlx-bf16")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

LetheanNetwork/lemrd-mlx-bf16

Gemma 4 in MLX format, full bf16 precision, converted from LetheanNetwork/lemrd's bf16 safetensors via mlx_lm.convert --dtype bfloat16 (no quantization). The full-precision reference for the MLX family. For the LEK-merged variant see lthn/lemrd.

License

Apache 2.0, subject to the Gemma Terms of Use.

Downloads last month
12
Safetensors
Model size
31B params
Tensor type
BF16
ยท
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for LetheanNetwork/lemrd-mlx-bf16

Finetuned
(2)
this model