We present CancerGPT, a novel single-cell RNA-seq foundation model (scFM) trained exclusively on malignant cells. Despite being trained on only one million total cells, a fraction of the data used by existing models, CancerGPT outperforms other scFMs in key tasks such as zero-shot batch integration and drug response prediction. During training, we employ tissue and technology-aware oversampling and domain-invariant training to enhance performance on underrepresented cancer types and sequencing technologies. We propose survival prediction as a new downstream task to evaluate the generalizability of single-cell foundation models to bulk RNA data and their applicability to patient stratification. CancerGPT demonstrates superior batch integration performance and shows significant improvements in predicting drug responses for both unseen cell lines and drugs. These results highlight the potential of focused, smaller foundation models in advancing drug discovery and our understanding of cancer biology.