mlx-community/DeepSeek-V4-Pro
This 8-bit model mlx-community/DeepSeek-V4-Pro was converted to MLX format from deepseek-ai/DeepSeek-V4-Pro.
DeepSeek-V4-Pro is a Mixture-of-Experts model with 1.6T total parameters, 49B activated parameters, and a context length of 1M tokens. Refer to the original model card for more details on the model.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-V4-Pro")
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)