# NanoVLMs: How small can we go and still make coherent Vision Language Models?

arXiv: https://arxiv.org/abs/2502.07838 · HTML: https://mlsanity.com/paper/2502.07838/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 11 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones](https://mlsanity.com/paper/2312.16862/) (2023)
- [BRAVE: Broadening the visual encoding of vision-language models](https://mlsanity.com/paper/2404.07204/) (2024)
- [Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions](https://mlsanity.com/paper/2404.07214/) (2024)
- [Deep Learning using Rectified Linear Units (ReLU)](https://mlsanity.com/paper/1803.08375/) (2018)
- [VCoder: Versatile Vision Encoders for Multimodal Large Language Models](https://mlsanity.com/paper/2312.14233/) (2023)
- [VividMed: Vision Language Model with Versatile Visual Grounding for Medicine](https://mlsanity.com/paper/2410.12694/) (2024)
- [StableMask: Refining Causal Masking in Decoder-only Transformer](https://mlsanity.com/paper/2402.04779/) (2024)
- [Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers](https://mlsanity.com/paper/2410.14072/) (2024)
- [Dragonfly: Multi-Resolution Zoom-In Encoding Enhances Vision-Language Models](https://mlsanity.com/paper/2406.00977/) (2024)
- [sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting](https://mlsanity.com/paper/2407.09879/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Survey on Efficient Vision-Language Models](https://mlsanity.com/paper/2504.09724/) (2025)
- [Attentions Under the Microscope: A Comparative Study of Resource Utilization for Variants of Self-Attention](https://mlsanity.com/paper/2507.07247/) (2025)

## Abstract (arXiv)

Vision-Language Models (VLMs), such as GPT-4V and Llama 3.2 vision, have garnered significant research attention for their ability to leverage Large Language Models (LLMs) in multimodal tasks. However, their potential is constrained by inherent challenges, including proprietary restrictions, substantial computational demands, and limited accessibility. Smaller models, such as GIT and BLIP, exhibit marked limitations, often failing to generate coherent and consistent text beyond a few tokens, even with extensive training. This underscores a pivotal inquiry: how small can a VLM be and still produce fluent and consistent text? Drawing inspiration from the exceptional learning process of 3-4 year old children, who rely heavily on visual cues for understanding and communication, we introduce two novel datasets: ShortDesc (featuring concise image descriptions) and LongDesc (containing more detailed image descriptions). These datasets consist of image-text pairs where the text is restricted to the simple vocabulary and syntax typically used by young children, generated with a scaled-down model, GPT-4o. Using these datasets, we demonstrate that it is possible to train VLMs that are significantly smaller, up to 10 times smaller than state of the art(SOTA) small VLMs while maintaining architectural simplicity. To evaluate the outputs, we leverage GPT-4o to grade the text, as if stories written by students, on creativity, meaningfulness, and consistency, assigning scores out of 10. This method addresses limitations of standard benchmarks by accommodating unstructured outputs and providing a multidimensional evaluation of the model capabilities. Our findings contribute to the development of lightweight, accessible multimodal models for resource constrained environments.