Quadro RTX 8000
GPU
44
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
8204tokens/s
1087tokens/s
Generation Speed
218tokens/s
36.7tokens/s
Time to First Token
163ms
1.17sec
LocalScore
2223
324
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium