Apple M4 Pro 10P+4E+20GPU
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
2037tokens/s
361tokens/s
186tokens/s
Generation Speed
112tokens/s
32.7tokens/s
17.6tokens/s
Time to First Token
625ms
3.44sec
6.87sec
LocalScore
723
151
78
COMPARE MODELS
4 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
Glm 4 9b Chat
Q4_K - Medium