Zach Mueller
@TheZachMueller
Head of Dev Rel at @LambdaAPI. Hardware nerd. Usually yelling at NCCL over things. Posts are my own.
808 Following 16K Followers
LUCAS ATKINS IS HERE TO TALK ABOUT TRAINING BIG MODELS 🫡
THE ONE. THE ONLY. THE JOE NEMOTRON IS HERE TO DISCUSS RL
Time to yap on some smol MoE’s today. If you’re around AI council, my talk is at 10!
Followed by the 🐐’s of @latkins, @ezi_ozoani, @llm_wizard, and @samsja19
Everything from pretraining at home to large scale RL
Show more
PinchBench results for Qwen3.5 27B using @UnslothAI K_XL quants, best of 3, thinking enabled.
TL;DR: Q3 KXL (14.5GB) or Q4 KXL (18GB)
While overall the "best" results showed little degradation, if you dig into mean/std Q4_K_XL overall was the best at ~84% on average.
Q3 seems viable, while Q2 is the the lowest performing, of course.
Show more
