cortexso/intellect-2

1---2license: apache-2.03pipeline_tag: text-generation4tags:5- cortex.cpp6- featured7---8 9## Overview10 11**Prime Intellect** released **INTELLECT-2**, a 32 billion parameter large language model (LLM) trained through distributed reinforcement learning on globally donated GPU resources. Built on the **Qwen2** architecture and fine-tuned with the **prime-rl** framework, INTELLECT-2 demonstrates strong performance in math, coding, and logical reasoning.12 13This model leverages GRPO (Generalized Reinforcement Policy Optimization) over verifiable rewards, introducing asynchronous distributed RL training with enhanced stability techniques. While its primary focus was on verifiable mathematical and coding tasks, it remains compatible with general-purpose text generation tasks.14 15## Variants16 17### INTELLECT-218 19| No | Variant                                                                         | Branch | Cortex CLI command                 |20|----|----------------------------------------------------------------------------------|--------|-----------------------------------|21| 1  | [INTELLECT-2 (32B)](https://huggingface.co/cortexso/intellect-2/tree/32b) | 32b    | `cortex run intellect-2:32b`      |22 23Each branch includes multiple GGUF quantized versions, optimized for various hardware configurations:24- **INTELLECT-2-32B:** q2_k, q3_k_l, q3_k_m, q3_k_s, q4_k_m, q4_k_s, q5_k_m, q5_k_s, q6_k, q8_025 26## Use it with Jan (UI)27 281. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)292. Use in Jan model Hub:30   ```bash31   cortexso/intellect-232   ```33 34## Use it with Cortex (CLI)35 361. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)372. Run the model with command:38   ```bash39   cortex run intellect-240   ```41 42## Credits43 44- **Author:** Prime Intellect45- **Converter:** [Menlo Research](https://menlo.ai/)46- **Original License:** [Apache-2.0](https://choosealicense.com/licenses/apache-2.0/)47- **Paper:** [Intellect 2 Technical Report](https://storage.googleapis.com/public-technical-paper/INTELLECT_2_Technical_Report.pdf)