| AI Model | Parameters/Tokens | Time |
| Gemini API | API (Served in Google Premises for benchmark with 2048 Tokens) | 11.839046239852905 Sec |
| LLAMA2 | Local LLM 7B Parameters | 70.02146315574646 Sec |
| Gemma | Local LLM 2B Parameters | 12.049653768539429 Sec |
| TinyLLama | Local LLM 1B Parameters | 8.009777784347534 Sec |
| Phi | Local LLM 3B Parameters | 8.246773719787598 Sec |
| mistral | Local LLM 7B Parameters | 16.776710987091064 Sec |
| CodeLLama | Local LLM 7B Parameters | 37.79871463775635Sec |