CPU
15.6
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
DeepSeek R1 Distill Qwen 1.5B
Q4_K - Medium1.8B
Qwen2.5 Coder 3B Instruct
Q4_K - Medium3.4B
Prompt Speed
14tokens/s
12tokens/s
5tokens/s
Generation Speed
4.5tokens/s
4.2tokens/s
2.1tokens/s
Time to First Token
100.32sec
128.28sec
269.94sec
LocalScore
9
7
3
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
DeepSeek R1 Distill Qwen 1.5B
Q4_K - Medium
Qwen2.5 Coder 3B Instruct
Q4_K - Medium