NVIDIA GeForce RTX 2060
GPU
6
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Gemma 3 4b It
Q6_K4.6B
Prompt Speed
4875tokens/s
716tokens/s
Generation Speed
168tokens/s
24.9tokens/s
Time to First Token
284ms
2.15sec
LocalScore
1422
202
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Gemma 3 4b It
Q6_K