Your chats

Models

What can I help with?

Intelli Hub can make mistakes. Check important info.

Select Model

Llama 3.3 70B

Most capable model, best for complex tasks

Recommended

Llama 3.3 70B Turbo

Fastest 70B model with speculative decoding

Fast

Llama 3.1 8B

Ultra-fast responses, good for simple queries

Fastest

Mixtral 8x7B

Balanced performance with long context

Gemma 2 9B

Efficient and versatile

Temperature

0.7

Enable Streaming