Just days after @AIatMeta
's Llama 3.3 70B model dropped, we've optimized it for our RDU hardware & it's live on SambaNova Cloud! #AI devs, try it out now & experience speeds of 400+ tokens/second! Learn more here
SambaNova Optimizes Meta’s Llama 3.3 for 400+ Token/Second Speed
By
–
