BLOOMChat is an open-source, multilingual chat Large Language Model (LLM) developed by SambaNova, a software company specializing in generative AI solutions, in collaboration with Together, an open, scalable, and decentralized cloud for Artificial Intelligence. Built on top of the BLOOM model, BLOOMChat is a 176-billion-parameter LLM capable of generating text in 46 natural languages and 13 programming languages. BLOOM, created by the international BigScience organization, represents the first language model with over 100 billion parameters for languages such as Spanish, French, and Arabic. To develop BLOOMChat, SambaNova and Together utilized the SambaNova DataScale systems, which employ SambaNova's unique Reconfigurable Dataflow Architecture for the training process. Synthetic conversation data and human-written samples were combined to create BLOOMChat. The OpenChatKit dataset served as the basis for chat functionality, while higher-quality human-generated datasets like Dolly 2.0 and OASST1 enhanced the model's performance. BLOOMChat's code and scripts for instruction-tuning are available on SambaNova's GitHub. In human evaluations, BLOOMChat outperformed competing models. Its responses were preferred over GPT-4 responses 45.25% of the time and ranked as the best among other open-source chat-aligned models in six languages 65.92% of the time. BLOOMChat also performed well in the WMT translation test, surpassing additional BLOOM model iterations and popular open-source conversation models. However, BLOOMChat faces limitations, such as generating factually incorrect or irrelevant information, switching languages unintentionally, repeating phrases, and producing toxic content. Ongoing research aims to address these challenges and optimize the chatbot's performance.