mlx-community/Phi-3.5-MoE-instruct-8bit

The Model mlx-community/Phi-3.5-MoE-instruct-8bit was converted to MLX format from microsoft/Phi-3.5-MoE-instruct using mlx-lm version 0.17.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Phi-3.5-MoE-instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)