Apple M1 4P+4E+7GPU
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
540tokens/s
80tokens/s
41tokens/s
Generation Speed
38.4tokens/s
9.1tokens/s
4.8tokens/s
Time to First Token
2.40sec
15.23sec
31.76sec
LocalScore
205
36
18
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