# Prime Intellect Releases prime-rl 0.6.0 to Train Trillion-Parameter MoE Models on Agentic RL Workloads

> Source: <https://www.marktechpost.com/2026/06/23/prime-intellect-releases-prime-rl-0-6-0-to-train-trillion-parameter-moe-models-on-agentic-rl-workloads/>
> Published: 2026-06-23 07:20:44+00:00

Prime Intellect has released prime-rl 0.6.0, an open framework for asynchronous reinforcement learning on trillion-parameter Mixture-of-Experts models. It trained GLM-5 on SWE tasks at up to 131k sequence length, with sub-5-minute step times and 256 rollouts, on 28 H200 nodes. This breakdown covers the inference and training optimizations behind those numbers — FP8 inference, Wide Expert Parallelism, prefill/decode disaggregation, router replay, and 3-D parallelism (FSDP, EP, CP).

The post [Prime Intellect Releases prime-rl 0.6.0 to Train Trillion-Parameter MoE Models on Agentic RL Workloads](https://www.marktechpost.com/2026/06/23/prime-intellect-releases-prime-rl-0-6-0-to-train-trillion-parameter-moe-models-on-agentic-rl-workloads/) appeared first on [MarkTechPost](https://www.marktechpost.com).