mlx-community/Meta-Llama-3.1-8B-8bit

The Model mlx-community/Meta-Llama-3.1-8B-8bit was converted to MLX format from meta-llama/Meta-Llama-3.1-8B using mlx-lm version 0.16.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Meta-Llama-3.1-8B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
24
Safetensors
Model size
2.26B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including mlx-community/Meta-Llama-3.1-8B-8bit