Apple M4 Max 12P+4E+40GPU
GPU
64
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
3868tokens/s
636tokens/s
339tokens/s
Generation Speed
180tokens/s
52.4tokens/s
29.6tokens/s
Time to First Token
303ms
1.85sec
3.55sec
LocalScore
1320
262
141
COMPARE MODELS
4 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
LLaMA v2
Q4_0