Resources

SambaNova has broken the 1000 t/s barrier: why it's a big deal for enterprise AI

Written by Keith Parker | May 29, 2024

SambaNova is the clear winner of the latest large language model (LLM) benchmark by Artificial Analysis. Topping the leaderboard at over 1000 tokens per second (t/s), Samba-1 Turbo sets a new record for Llama 3 8B performance on a single SN40L node and with full precision.