BlueLM-2.5-3B Technical Report

TL;DR

BlueLM-2.5-3B is a compact, versatile multimodal large language model capable of both thinking and non-thinking modes, optimized for edge deployment with strong performance across multimodal and text benchmarks.

Contribution

First 3B-scale MLLM supporting both thinking and non-thinking modes with explicit control over thinking tokens, developed through diversified data and hybrid reinforcement learning.

Findings

Achieves performance comparable to larger models in thinking mode.

Outperforms smaller models in non-thinking mode on multimodal benchmarks.

Exhibits high data efficiency with less training data than larger counterparts.

Abstract

We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reasoning capabilities. To the best of our knowledge, this is the first 3B-scale MLLM to support both thinking and non-thinking modes, while also enabling explicit control over thinking token budget. BlueLM-2.5-3B is developed through diversified data curation, key data resampling, hybrid heterogeneous reinforcement learning, and a high-performance training infrastructure. Our model achieves superior multimodal capacity while preserving competitive pure-text performance with only 2.9 billion parameters. We conduct comprehensive evaluations across a broad range of multimodal and text-only benchmarks. In thinking mode, BlueLM-2.5-3B achieves comparable performance to Qwen3-4B on text-only benchmarks, and trails the larger Kimi-VL-A3B-16B by only about 5% on average across multimodal evaluations. In non-thinking mode, it outperforms Qwen2.5-VL-3B on the majority of multimodal benchmarks. Additionally, BlueLM-2.5-3B exhibits exceptional data efficiency. All of the aforementioned performance is achieved with substantially less total training data than Qwen2.5-VL-3B and Qwen3-4B. We hope our work contributes to the advancement of high-performance, on-device MLLMs and provides meaningful insights to the research community.