Intel Xeon Gold 5218 CPU @ 2.30GHz (cascadelake)
CPU
754.5
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
357tokens/s
29tokens/s
Generation Speed
71.1tokens/s
8.6tokens/s
Time to First Token
4.01sec
47.14sec
LocalScore
185
17
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium