NVIDIA L40S-8Q
GPU
8
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Prompt Speed
12563tokens/s
343tokens/s
Generation Speed
62.4tokens/s
3.5tokens/s
Time to First Token
110ms
5.74sec
LocalScore
1925
59
COMPARE MODELS
2 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium