Apple M2 4P+4E+10GPU
GPU
16
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
802tokens/s
141tokens/s
75tokens/s
Generation Speed
55.6tokens/s
14.7tokens/s
8.1tokens/s
Time to First Token
1.59sec
9.13sec
17.30sec
LocalScore
304
61
33
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