Apple M5 Max 6P+12E+40GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
4331tokens/s
360tokens/s
Generation Speed
263tokens/s
36.9tokens/s
Time to First Token
269ms
3.30sec
LocalScore
1618
159
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium