Apple M4 Max 12P+4E+40GPU
GPU
64
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
LLaMA v2
Q4_06.7B
Prompt Speed
3901tokens/s
692tokens/s
Generation Speed
182tokens/s
62.5tokens/s
Time to First Token
302ms
1.73sec
LocalScore
1330
293
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
LLaMA v2
Q4_0