Apple M4 Max 12P+4E+40GPU
GPU
48
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
3858tokens/s
663tokens/s
328tokens/s
Generation Speed
180tokens/s
54.2tokens/s
28.0tokens/s
Time to First Token
308ms
1.80sec
3.60sec
LocalScore
1312
271
137
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