Downloads · 30 days
58
1% of all-time downloads
GRM-2.5
OrionLLM/GRM-2.5
GRM-2.5 is a image-text-to-text model from OrionLLM. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
<p align="center" <img src="https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/sZK90f3KIE6JcF4Nrm2g.png" alt="logo" width="500" </p <div align="center" <a href="https://huggingface.co/Orion…
All-time downloads
5.2K
Public
Parameters
4.7B
9.3 GB on disk
Likes
27
Public
Repo makeup
Click a slice to open those files.
.safetensors9.3 GB · 100%
Parameter types
How the weights are stored.
BF164.7B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
GRM-2.5
<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/sZK90f3KIE6JcF4Nrm_2g.png" alt="logo" width="500"> </p> <div align="center"> <a href="https://huggingface.co/OrionLLM/GRM-2.5/" style="text-decoration: none;"> <img src="https://img.shields.io/badge/🤗-HuggingFace-FC926C?style=for-the-badge" alt="HuggingFace"> </a> <a href="https://huggingface.co/collections/OrionLLM/grm-25" style="text-decoration: none;"> <img src="https://img.shields.io/badge/📚-Collection-3B82F6?style=for-the-badge" alt="Collection"> </a> <a href="https://www.apache.org/licenses/LICENSE-2.0" style="text-decoration: none;"> <img src="https://img.shields.io/badge/📜-License-E343BD?style=for-the-badge" alt="License"> </a> </div>1. Introduction
GRM-2.5 is a 4B-parameter reasoning model built for general-purpose local AI. It is designed to deliver strong performance across a wide range of tasks while remaining efficient and accessible for local inference.
The model is optimized for structured reasoning, helping it produce more accurate, coherent, and reliable responses on complex problems. GRM-2.5 aims to combine strong reasoning ability, practical usability, and efficient deployment in a compact form factor.
2. Key Capabilities
- Strong Reasoning for Everyday and Advanced Tasks: GRM-2.5 is built to handle both daily conversations and more demanding reasoning workloads with clarity and consistency.
- Efficient Local Coding and Agentic Use: Despite its compact size, the model is well suited for code generation, structured problem-solving, and local agent-style workflows.
- Optimized for Local Deployment: GRM-2.5 is designed for accessible inference across a broad range of hardware, making it a practical choice for users who want capable AI running locally.
3. Performance
GRM-2.5 is designed to be a highly capable option for local AI use across many scenarios. It performs well in complex reasoning tasks, everyday chat, coding, and agentic workflows, while maintaining the efficiency expected from a compact 4B model.
Its focus is not only raw capability, but also practical intelligence: strong reasoning, stable long-context behavior, and usability on consumer hardware.
<table> <tr> <th style="background: rgba(128,128,128,0.1); text-align: center;"> </th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-2.5-Plus (Closed)</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-2.5</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-2.5-Air</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-7B</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">GRM-1.5B</th> </tr> <tr> <td align="center" colspan="6" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Knowledge & STEM</i></td> </tr> <tr> <td align="center">MMLU-Pro</td> <td align="center"><b>84.2</b></td> <td align="center"><b>80.1</b></td> <td align="center"><b>43.6</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">GPQA Diamond</td> <td align="center"><b>82.7</b></td> <td align="center"><b>76.7</b></td> <td align="center"><b>12.5</b></td> <td align="center">53.7</td> <td align="center">29.5</td> </tr> <tr> <td align="center" colspan="6" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Instruction Following</i></td> </tr> <tr> <td align="center">IFEval</td> <td align="center"><b>91.8</b></td> <td align="center"><b>90.2</b></td> <td align="center"><b>44.5</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">MultiChallenge</td> <td align="center"><b>56.5</b></td> <td align="center"><b>49.8</b></td> <td align="center"><b>19.3</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center" colspan="6" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Reasoning & Coding</i></td> </tr> <tr> <td align="center">HMMT Feb 25</td> <td align="center"><b>84.4</b></td> <td align="center"><b>75.2</b></td> <td align="center"><b>--</b></td> <td align="center">42.7</td> <td align="center">27.3</td> </tr> <tr> <td align="center">HMMT Nov 25</td> <td align="center"><b>83.2</b></td> <td align="center"><b>77.2</b></td> <td align="center"><b>--</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">LiveCodeBench v6</td> <td align="center"><b>67.2</b></td> <td align="center"><b>56.9</b></td> <td align="center"><b>--</b></td> <td align="center">51.7</td> <td align="center">39.4</td> </tr> <tr> <td align="center" colspan="6" style="background: linear-gradient(90deg, rgba(124,58,237,0.45) 0%, rgba(99,102,241,0.42) 50%, rgba(59,130,246,0.45) 100%); font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Agent</i></td> </tr> <tr> <td align="center">TAU2-Bench</td> <td align="center"><b>80.5</b></td> <td align="center"><b>80.2</b></td> <td align="center"><b>11.6</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">DeepPlanning</td> <td align="center"><b>18.6</b></td> <td align="center"><b>17.9</b></td> <td align="center"><b>--</b></td> <td align="center">--</td> <td align="center">--</td> </tr> <tr> <td align="center">OSWorld-Verified</td> <td align="center"><b>42.4</b></td> <td align="center"><b>36.0</b></td> <td align="center"><b>--</b></td> <td align="center">--</td> <td align="center">--</td> </tr> </table>4. Family
The GRM-2.5 family is available in various sizes to suit every case.
<table> <tr> <th style="background: rgba(128,128,128,0.1); text-align: center;">Model</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Size</th> <th style="background: rgba(128,128,128,0.1); text-align: center;">Domain</th> </tr> <tr> <td align="center">GRM-2.5-Plus</td> <td align="center">9B</td> <td align="center">Closed model for research and agent purposes</td> </tr> <tr> <td align="center">GRM-2.5</td> <td align="center">4B</td> <td align="center">Powerful on-device deployment for difficult tasks</td> </tr> <tr> <td align="center">GRM-2.5-Air</td> <td align="center">0.8B</td> <td align="center">Any-device deployment for everyday chat</td> </tr> </table>5. Architecture
GRM-2.5 is built on the Qwen3.5 architecture and is optimized for complex tasks, agent environments, and everyday chat.
GRM-2.5 applies the same principle to a stronger, larger foundation, resulting in a model that punches above its weight class on structured reasoning tasks while remaining deployable on consumer hardware.
<div align="center">
GRM-2.5 is developed by OrionLLM and released under the Apache 2.0 License.
</div>- Task
- Image-Text-to-Text
- Type
- qwen3_5
- License
- apache-2.0
- Created
- Apr 7, 2026
- Updated
- Apr 29, 2026