llama3.1-8b-instruct-mlx-8bit
A MLX converted and 8-bit quantized version of llama3.1-8b-instruct. Converted using mlx-lm 0.31.1.
- Downloads last month
- 42
Model size
8B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for justindal/llama3.1-8b-instruct-mlx-8bit
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct Finetuned
justindal/llama3.1-8b-instruct-mlx