Premium models

Llama3-8b-Instruct

Tokens per second: ~550

Llama3.1-8b-Instruct

Tokens per second: ~350

TinyLlama-1.1b

Tokens per second: ~80

Gemma-7b-it

Tokens per second: ~300

stable-diffusion-xl-base-1.0

Response time: ~12.00 seconds