Tesla P40
GPU
24
GB
PERFORMANCE OVERVIEW
Model
Llama 3.2 1B Instruct
Q4_K - Medium1.5B
Qwen2.5 14B Instruct
Q4_K - Medium14.8B
Qwen3-30B-A3B
Q4_K - Medium30.5B
Prompt Speed
2662tokens/s
329tokens/s
289tokens/s
Generation Speed
105tokens/s
15.4tokens/s
29.2tokens/s
Time to First Token
558ms
3.74sec
4.10sec
LocalScore
832
112
127
COMPARE MODELS
7 models tested
Select Models
Llama 3.2 1B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q4_K - Medium
Qwen2.5 14B Instruct
Q8_0
Qwen3-30B-A3B
Q4_K - Medium
LLaMA v2
Q4_0