Edit model card

mlx-community/Meta-Llama-3.1-405B-2bit

The Model mlx-community/Meta-Llama-3.1-405B-2bit was converted to MLX format from meta-llama/Meta-Llama-3.1-405B using mlx-lm version 0.16.1.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Meta-Llama-3.1-405B-2bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
Downloads last month
0
Safetensors
Model size
38.4B params
Tensor type
FP16
·
U32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.