NVIDIA GeForce GTX 1070 with Max-Q Design
GPU
8
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Prompt Speed
814tokens/s
Generation Speed
24.4tokens/s
Time to First Token
1.83sec
LocalScore
221
COMPARE MODELS
1 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium