Apple M4 Max 10P+4E+32GPU
GPU
36
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
3211tokens/s
551tokens/s
262tokens/s
Generation Speed
169tokens/s
47.2tokens/s
24.3tokens/s
Time to First Token
371ms
2.20sec
4.65sec
LocalScore
1136
228
111
COMPARE MODELS
9 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
Mistral Small 24B Instruct 2501
Q4_K - Small
DeepSeek R1 Distill Qwen 1.5B
Q4_K - Medium