Groq
Models
-
Groq Llama is Meta’s Llama family served on Groq hardware, giving Llama-quality outputs with very low latency.TextReleased 1y ago
-
Groq Gemma is Google’s Gemma model family served on Groq hardware for ultra-low-latency inference. You get Gemma’s capabilities with extremely fast response times.TextReleased 2y ago
