You can see the various quantizations here, both for the 2B model and the 7B model. The smallest you can go is the q2_K quantization of the 2B model, which is 1.3GB, but I wouldn't really call that "functional". The q4_0 quantization is 1.7GB, and that would probably be functional.
The size of anything but the model is going to be rounding error compared to how large the models are, in this context.
What's the use case of models this small? Can you use the "knowledge" encoded in them and ask them questions and get relevant answers, or are they used as text processors to summarize documents etc?
Gemma 2B generation quality is excellent in my own very-biased opinion. I asked it to write a response to your comment:
--
Large language models (LLMs) have achieved significant progress in recent years, with models like GPT-3 and LaMDA demonstrating remarkable abilities in various tasks such as language generation, translation, and question answering.
However, 2b parameter models are a much smaller and simpler type of LLM compared to GPT-3. While they are still capable of impressive performance, they have a limited capacity for knowledge representation and reasoning.
Despite their size, 2b parameter models can be useful in certain scenarios where the specific knowledge encoded in the model is relevant to the task at hand. For example:
- Question answering: 2b parameter models can be used to answer questions by leveraging their ability to generate text that is similar to the question.
- Text summarization: 2b parameter models can be used to generate concise summaries of documents by extracting the most important information.
- Code generation: While not as common, 2b parameter models can be used to generate code snippets based on the knowledge they have learned.
Overall, 2b parameter models are a valuable tool for tasks that require specific knowledge or reasoning capabilities. However, for tasks that involve general language understanding and information retrieval, larger LLMs like GPT-3 may be more suitable.
--
Generated in under 1s from query to full response on together.ai
You can see the various quantizations here, both for the 2B model and the 7B model. The smallest you can go is the q2_K quantization of the 2B model, which is 1.3GB, but I wouldn't really call that "functional". The q4_0 quantization is 1.7GB, and that would probably be functional.
The size of anything but the model is going to be rounding error compared to how large the models are, in this context.