TinyChart is an efficient multimodal large language model (MLLM) designed for chart understanding with only 3 billion parameters. It addresses two key challenges in efficient chart understanding: (1) reducing the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, which trains the model to generate Python programs for numerical calculations, and (2) reducing lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module, which gradually merges most similar vision tokens. Extensive experiments show that TinyChart achieves state-of-the-art performance on various chart understanding benchmarks, including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart understanding MLLMs with up to 13B parameters, such as ChartLlama and ChartAst, and closed-source general-purpose MLLMs like GPT-4V on ChartQA. It also demonstrates superior efficiency with higher throughput during inference due to its smaller model scale and more efficient vision encoding. The code and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.TinyChart is an efficient multimodal large language model (MLLM) designed for chart understanding with only 3 billion parameters. It addresses two key challenges in efficient chart understanding: (1) reducing the burden of learning numerical computations through a Program-of-Thoughts (PoT) learning strategy, which trains the model to generate Python programs for numerical calculations, and (2) reducing lengthy vision feature sequences produced by the vision transformer for high-resolution images through a Vision Token Merging module, which gradually merges most similar vision tokens. Extensive experiments show that TinyChart achieves state-of-the-art performance on various chart understanding benchmarks, including ChartQA, Chart-to-Text, Chart-to-Table, OpenCQA, and ChartX. It outperforms several chart understanding MLLMs with up to 13B parameters, such as ChartLlama and ChartAst, and closed-source general-purpose MLLMs like GPT-4V on ChartQA. It also demonstrates superior efficiency with higher throughput during inference due to its smaller model scale and more efficient vision encoding. The code and model are available at https://github.com/X-PLUG/mPLUG-DocOwl/tree/main/TinyChart.