Apple M4 Pro 8P+4E+16GPU
GPU
24
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
meta-llama-7b
Q5_K - Medium6.7B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Prompt Speed
1846tokens/s
291tokens/s
292tokens/s
Generation Speed
111tokens/s
24.4tokens/s
30.3tokens/s
Time to First Token
669ms
4.30sec
4.27sec
LocalScore
674
118
128
COMPARE MODELS
5 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
meta-llama-7b
Q5_K - Medium
LLaMA v2
Q8_0
Gemma 3 27b It
IQ2_M - 2.7 bpw