Apple M2 Ultra 16P+8E+60GPU
GPU
128
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
3296tokens/s
377tokens/s
Generation Speed
176tokens/s
33.6tokens/s
Time to First Token
334ms
3.10sec
LocalScore
1203
160
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium