Phi-3
Collection
14 items • Updated • 6
mlx-community/Phi-3-small-8k-instruct-AQ4_32
The Model mlx-community/Phi-3-small-8k-instruct-AQ4_32 was converted to MLX format from microsoft/Phi-3-small-8k-instruct using mlx-lm version 0.14.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Phi-3-small-8k-instruct-AQ4_32")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 32
Model size
7B params
Tensor type
U32
·
F16 ·
Hardware compatibility
Log In to add your hardware
Quantized