@0xn13
🚀 Meet INTELLECT-3 by Prime Intellect: a 106B Mixture-of-Experts model trained on GLM-4.5 Air Base with SFT & large-scale asynchronous RL as core training.
It excels in math, code & reasoning, focusing on long action chains & agent tasks.
Open code & tools here: https://huggingface.co/PrimeIntellect/INTELLECT-3
0 reply
0 recast
1 reaction