Apple M2 Max 8P+4E+38GPU
GPU
96
GB
PERFORMANCE OVERVIEW
Model
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
484tokens/s
252tokens/s
Generation Speed
46.4tokens/s
25.2tokens/s
Time to First Token
2.44sec
4.80sec
LocalScore
210
110
COMPARE MODELS
2 models tested
Select Models
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium