Microsoft processed 3.8 billion parameters in the Phi-3 Mini. The LLM is significantly smaller than general knowledge competitors GPT-4 and Llama 3, but focuses on vertical applications.

The latest version of Microsoft’s smallest LLM (Large Language Model), Phi-3, is now available on Azure, Hugging Face and Ollama. The model is available in three flavors:

• Phi-3 Mini with 3.8 billion parameters (now available)
• Phi-3 Small with 7 billion parameters (coming soon)
• Phi-3 medium with 14 billion parameters (coming soon)

At the end of last year, Microsoft launched its predecessor Phi-2, the smallest model of which contained 2.7 billion parameters. The latest version is said to perform better and deliver answers comparable to LLMs 10 times larger.

The big advantage of small AI models is that they require less energy to operate. This reduces energy costs and makes mobile applications possible. Microsoft isn’t the only one working on small LLMs. Google has, among other things, two variants: Gemma (2 billion and 7 billion parameters). Anthropic also has a compact version of Claude 3 called Haiku. Last week, Meta launched Llama 3 in two variants: 8 billion and 70 billion parameters.

Microsoft says it trained Phi-3 with a “curriculum” inspired by how children learn from bedtime stories. The focus of Phi-3 is on coding and reasoning. The software giant says smaller LLMs are a logical choice for many companies. Their internal data sets are more compact and models like Phi-3 are cheaper to run because they require less computing power and energy.

Curious for more information about artificial intelligence? Then be sure to take a look at our AI topic page with video and three interesting, detailed articles.