Modelpublic

OrionLLM/GRM-3.2-Turf

sourceHugging Faceapache-2.0updated 3d agoView on Hugging Face

11likes422downloads

Model Card

1. Introduction

We're introducing GRM-3.2-Turf, our lightweight model built for difficult reasoning problems and general conversation in local environments. GRM-3.2-Turf marks a substantial leap over its predecessor, GRM-2.6-Air-Opus, and is designed to serve as a dependable engine for low-resource devices with low processing power.

The model is purpose-built to deliver efficient execution without sacrificing structured reasoning capability, making it ideal for mobile devices, embedded systems, and local deployments where memory and compute constraints are critical.

2. Key Capabilities

—On-Device Efficiency: Engineered to run smoothly on low-resource hardware with minimal memory footprint and fast inference latency.
—Enhanced Local Reasoning: Substantial leap over GRM-2.6-Air-Opus in structured reasoning, problem-solving, and general conversation tasks.
—High-Fidelity Instruction Following: Exceptional capability in handling constrained prompts, complex system instructions, and precise response formatting.
—Robust Tool Use: Strong performance in tool calling and function execution, enabling agentic workflows in lightweight environments.

3. Performance

GRM-3.2-Turf is designed as our premier lightweight model for local execution. It builds directly on the strengths of GRM-2.6-Air-Opus while setting new benchmarks for sub-2B reasoning and instruction-following capability on edge hardware.

[image]

Detailed Benchmarks

<div align="center"> <div style="display:inline-block; max-width:100%; border-radius:20px; overflow:hidden;"> <table style="margin:0; border-collapse:collapse; border-radius:20px;"> <tr> <th style="background: rgba(128,128,128,0.1); text-align: center; border: hidden;"> </th> <th style="background: rgba(128,128,128,0.1); text-align: center; border: hidden;">GRM-3.2-Turf</th> <th style="background: rgba(128,128,128,0.1); text-align: center; border: hidden;">LFM2.5-1.2B-Thinking</th> <th style="background: rgba(128,128,128,0.1); text-align: center; border: hidden;">Qwen3.5-2B</th> <th style="background: rgba(128,128,128,0.1); text-align: center; border: hidden;">Gemma-4-E2B</th> </tr> <tr> <td align="center" colspan="5" style="background: rgba(165,105,60,0.45); border: hidden; font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Knowledge & STEM</i></td> </tr> <tr> <td style="text-align:left; padding:9px 10px 9px 18px; border: hidden;"><div style="font-size:15px; font-weight:600; line-height:1.22;">Multidisciplinary knowledge</div><div style="margin-top:4px; font-size:11px; font-weight:400; line-height:1.2; opacity:0.62;">MMLU-Pro</div></td> <td align="center" style="background: rgba(165,105,60,0.16); vertical-align:middle;">56.2</td> <td align="center" style="vertical-align:middle;">49.65</td> <td align="center" style="vertical-align:middle;"><b>66.5</b></td> <td align="center" style="vertical-align:middle;">60.0</td> </tr> <tr> <td style="text-align:left; padding:9px 10px 9px 18px; border: hidden;"><div style="font-size:15px; font-weight:600; line-height:1.22;">Scientific reasoning</div><div style="margin-top:4px; font-size:11px; font-weight:400; line-height:1.2; opacity:0.62;">GPQA Diamond</div></td> <td align="center" style="background: rgba(165,105,60,0.16); vertical-align:middle;">42.4</td> <td align="center" style="vertical-align:middle;">37.86</td> <td align="center" style="vertical-align:middle;"><b>51.6</b></td> <td align="center" style="vertical-align:middle;">43.4</td> </tr> <tr> <td align="center" colspan="5" style="background: rgba(165,105,60,0.45); border: hidden; font-weight: bold; height:32px; padding-top:2px; padding-bottom:2px;"><i>Instruction Following & Function Calling</i></td> </tr> <tr> <td style="text-align:left; padding:9px 10px 9px 18px; border: hidden;"><div style="font-size:15px; font-weight:600; line-height:1.22;">Instruction following</div><div style="margin-top:4px; font-size:11px; font-weight:400; line-height:1.2; opacity:0.62;">IFEval</div></td> <td align="center" style="background: rgba(165,105,60,0.16); vertical-align:middle;"><b>91.2</b></td> <td align="center" style="vertical-align:middle;">88.42</td> <td align="center" style="vertical-align:middle;">78.6</td> <td align="center" style="vertical-align:middle;">—</td> </tr> <tr> <td style="text-align:left; padding:9px 10px 9px 18px; border: hidden;"><div style="font-size:15px; font-weight:600; line-height:1.22;">Complex instruction following</div><div style="margin-top:4px; font-size:11px; font-weight:400; line-height:1.2; opacity:0.62;">IFBench</div></td> <td align="center" style="background: rgba(165,105,60,0.16); vertical-align:middle;"><b>46.8</b></td> <td align="center" style="vertical-align:middle;">44.85</td> <td align="center" style="vertical-align:middle;">41.3</td> <td align="center" style="vertical-align:middle;">—</td> </tr> <tr> <td style="text-align:left; padding:9px 10px 9px 18px; border: hidden;"><div style="font-size:15px; font-weight:600; line-height:1.22;">Function calling</div><div style="margin-top:4px; font-size:11px; font-weight:400; line-height:1.2; opacity:0.62;">BFCL v3</div></td> <td align="center" style="background: rgba(165,105,60,0.16); vertical-align:middle;"><b>59.3</b></td> <td align="center" style="vertical-align:middle;">56.97</td> <td align="center" style="vertical-align:middle;">—</td> <td align="center" style="vertical-align:middle;">—</td> </tr> </table> </div> </div>

Scores are taken from each provider's own published model card, blog post, or evaluation benchmark suite.

4. Family

The GRM-3.2 family is available in various sizes to suit every use case.

5. Architecture

GRM-3.2-Turf is built on the LiquidAI/LFM2.5-1.2B-Thinking base architecture, a 1.2B-parameter model optimized for reasoning, general conversation, and tool use, specifically tailored for efficient deployment on resource-constrained hardware.

GRM-3.2-Turf is developed by [OrionLLM](https://huggingface.co/OrionLLM) and released under the Apache 2.0 License.

</div>