Do post speed and accuracy benchmarks if you are able to run this

#2
by daryl149 - opened

The current number 1 on the LLM leaderboard, only 34B, 200k context and now quantized with AWQ. This could very well be the optimal model in terms of model size, model accuracy and model speed.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment