Apple M1 4P+4E+8GPU
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
584tokens/s
84tokens/s
53tokens/s
Generation Speed
39.8tokens/s
8.9tokens/s
5.4tokens/s
Time to First Token
2.24sec
14.35sec
24.55sec
LocalScore
218
37
23
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