Llama 3.2
Collection
Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models.
•
15 items
•
Updated
•
10
mlx-community/Llama-3.2-1B-Instruct-8bit
The Model mlx-community/Llama-3.2-1B-Instruct-8bit was converted to MLX format from meta-llama/Llama-3.2-1B-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/Llama-3.2-1B-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 219,698