typealias/Llama-3-6B-Instruct-pruned-mlx-4bit
The Model typealias/Llama-3-6B-Instruct-pruned-mlx-4bit was converted to MLX format from kuotient/Llama-3-6B-Instruct-pruned using mlx-lm version 0.13.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("typealias/Llama-3-6B-Instruct-pruned-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
- Downloads last month
- 5
Model size
1.0B params
Tensor type
F16
·
U32
·
Hardware compatibility
Log In
to add your hardware
Quantized
Model tree for typealias/Llama-3-6B-Instruct-pruned-mlx-4bit
Base model
meta-llama/Meta-Llama-3-8B-Instruct