Accelerator icon
Apple M3 Max 12P+4E+40GPU
GPU
48
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Prompt Speed
3395tokens/s
Generation Speed
150tokens/s
Time to First Token
348ms
LocalScore
1134
COMPARE MODELS

1 models tested

Select Models

Llama 3.2 1B Instruct

Q4_K - Medium

Apple M3 Max 12P+4E+40GPU - 48GB