Accelerator icon
Apple M4 Pro 10P+4E+20GPU
GPU
48
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
2128tokens/s
358tokens/s
189tokens/s
Generation Speed
118tokens/s
32.1tokens/s
17.8tokens/s
Time to First Token
580ms
3.49sec
6.65sec
LocalScore
756
149
80
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

Apple M4 Pro 10P+4E+20GPU - 48GB

0306090120tokens/s (higher is better)Llama 3.2 1B Instruct(Q4_K - Medium)Meta Llama 3.1 8BInstruct (Q4_K -Medium)Qwen2.5 14B Instruct(Q4_K - Medium)