Accelerator icon
Apple M4 4P+6E+10GPU
GPU
24
GB
PERFORMANCE OVERVIEW
Model
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Prompt Speed
159tokens/s
Generation Speed
16.6tokens/s
Time to First Token
7.93sec
LocalScore
69
COMPARE MODELS

1 models tested

Select Models

Meta Llama 3.1 8B Instruct

Q4_K - Medium

Apple M4 4P+6E+10GPU - 24GB