Llama 3, a computing model, is achieving impressive token speeds on @GroqInc, reaching up to 55 tokens/second, 400 billion running faster than GPT-4-turbo, and 8 billion exceeding 800 T/s. The model is expected to be integrated into Groq's operations.
Llama 3 400b is gonna be running on groq faster than GPT-4-turbo and at the same level of quality 😳 https://t.co/gPRSEGMWLl
Llama 3 8b running at upwards of 800 T/s on groq 😲 https://t.co/W3I8Or3Uqb
Llama 3 is on @GroqInc now 😄💥 https://t.co/Z8FkmKUKdd
Llama 3 in @GroqInc soon? Look the token speed/s 😳 https://t.co/w9wegzNmOl
We have Llama 3 running at 55 tokens/second on https://t.co/Rf1XocyTL2: https://t.co/iwC2zk69lj