Apple M3 Max 12P+4E+40GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
3292tokens/s
587tokens/s
303tokens/s
Generation Speed
146tokens/s
45.8tokens/s
25.5tokens/s
Time to First Token
358ms
2.05sec
4.11sec
LocalScore
1104
236
123
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium