Hacker News new | ask | show | jobs
by bearjaws 876 days ago
Together.ai seems to be the best, incredibly fast.
2 comments
T_S_ 872 days ago
Not so sure about that. Check out https://github.com/ray-project/llmperf-leaderboard

And try mixtral on chat.groq.com

link
RupertEisenhart 875 days ago
These guys are much faster than openrouter, and their llama2 runs faster than 3.5-turbo. Amazing work.
link