Apple M1 Max 8P+2E+32GPU
GPU
32
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
2022tokens/s
349tokens/s
189tokens/s
Generation Speed
126tokens/s
34.4tokens/s
19.4tokens/s
Time to First Token
560ms
3.58sec
6.56sec
LocalScore
768
150
82
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