NVIDIA GeForce RTX 3060
GPU
12
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
6130tokens/s
1490tokens/s
762tokens/s
Generation Speed
197tokens/s
52.2tokens/s
27.3tokens/s
Time to First Token
229ms
879ms
1.97sec
LocalScore
1737
446
228
COMPARE MODELS
8 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
gemma-2-9b-it
Q4_K - Medium
Gemma 3 4b It
Q6_K