Apple M3 Max 12P+4E+40GPU
GPU
48
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
3382tokens/s
287tokens/s
Generation Speed
150tokens/s
23.6tokens/s
Time to First Token
352ms
4.27sec
LocalScore
1131
117
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium