Apple M4 Pro 8P+4E+16GPU
GPU
24
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
1791tokens/s
297tokens/s
144tokens/s
Generation Speed
111tokens/s
30.5tokens/s
15.2tokens/s
Time to First Token
676ms
4.22sec
8.90sec
LocalScore
664
129
63
COMPARE MODELS
6 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
meta-llama-7b
Q5_K - Medium
LLaMA v2
Q8_0