Apple M1 Ultra 16P+4E
CPU
128
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
284tokens/s
72tokens/s
39tokens/s
Generation Speed
57.1tokens/s
15.2tokens/s
8.0tokens/s
Time to First Token
4.79sec
17.48sec
32.94sec
LocalScore
150
40
21
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