NVIDIA TITAN RTX
GPU
24
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Meta Llama 3.1 8B Instruct
Q4_K - Medium8.0B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
9273tokens/s
2226tokens/s
1229tokens/s
Generation Speed
217tokens/s
71.2tokens/s
40.2tokens/s
Time to First Token
144ms
574ms
1.03sec
LocalScore
2409
651
364
COMPARE MODELS
3 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Meta Llama 3.1 8B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium