AMD Radeon Pro V620
GPU
30
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Prompt Speed
3202tokens/s
Generation Speed
12.1tokens/s
Time to First Token
578ms
LocalScore
407
COMPARE MODELS
1 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium