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
13997tokens/s
4898tokens/s
Generation Speed
75.6tokens/s
55.8tokens/s
Time to First Token
294ms
374ms
LocalScore
1903
950
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium