NVIDIA RTX A5000
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
12138tokens/s
2891tokens/s
1532tokens/s
Generation Speed
310tokens/s
89.1tokens/s
50.4tokens/s
Time to First Token
110ms
446ms
837ms
LocalScore
3242
832
452
COMPARE MODELS
7 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
Ministral 8B Instruct 2410 TEST
Q4_K - Medium
Mistral Nemo Instruct 2407
Q4_K - Medium