NVIDIA GeForce RTX 5090
GPU
32
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
13214tokens/s
3790tokens/s
Generation Speed
69.3tokens/s
38.0tokens/s
Time to First Token
266ms
471ms
LocalScore
1815
705
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium