This is huge! the opensource community is all in on open access to rl environments, PrimeIntellect youβre not alone. Code: https://github.com/WooooDyy/AgentGym-RL
The models come in Thinking and Instruct versions and utilize a new architecture, allowing it to have ~10x faster inference than Qwen32B. π Step-by-step Guide: https://docs.unsloth.ai/models/qwen3-next