owen198/3cm
The Model owen198/3cm was converted to MLX format from meta-llama/Meta-Llama-3-8B using mlx-lm version 0.15.2.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("owen198/3cm")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 502
Model size
1B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized