NVIDIA GeForce RTX 5080
GPU
16
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
9736tokens/s
1927tokens/s
Generation Speed
43.9tokens/s
14.4tokens/s
Time to First Token
140ms
658ms
LocalScore
1450
348
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium