Apple M3 Ultra 24P+8E+80GPU
GPU
512
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
5483tokens/s
1100tokens/s
576tokens/s
Generation Speed
179tokens/s
62.6tokens/s
35.8tokens/s
Time to First Token
209ms
1.07sec
2.05sec
LocalScore
1674
401
216
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