There are to be about ten Large Language Models to be used from the server, with new features to be
Such as real time stock broking, image and video generation and news synopsis aggregator.
Gemma3: The current most capable model that runs on a single GPU.
Llama4: Meta's latest collection of multimodal models.
gemma2: Google Gemma 2 is a high-performing and efficient model by now available in the 2B size.
llava: LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder an
llama3: Meta Llama 3: The most capable openly available LLM to date.
llama2: Llama 2 is a collection of foundation language models ranging from the 7B parameter size
orca-mini: A general-purpose model using the 3 billion parameter size.
Aya: Aya 23 is a new family of state-of-the-art, multilingual models that supports 23 languages in t
wizard-math: A Model focused on math and logic problems.Neural-chat: A fine-tuned model.