description Phi-3-mini-4k-instruct Overview
Phi-3-mini-4k-instruct is a 3.8-billion-parameter instruction-tuned language model developed by Microsoft as part of the Phi-3 family of small language models. The model is designed for efficiency and can run on local hardware, with a 4,000-token context window. Microsoft released the model weights openly for research and development use. JetBrains provides integration for Phi-3-mini-4k-instruct in its IDEs as a self-hosted AI assistant option for developers.
help Phi-3-mini-4k-instruct FAQ
How large is Phi-3-mini-4k-instruct?
Phi-3-mini-4k-instruct is a Microsoft language model with approximately 3.8 billion parameters. It is designed as a lightweight instruction-following model rather than a frontier-scale system.
What does the 4K name mean in Phi-3-mini-4k-instruct?
The 4K refers to its context length of roughly 4,000 tokens. Microsoft also released a separate Phi-3 Mini variant with a much longer 128K-token context.
Can Phi-3-mini-4k-instruct run locally?
Yes. The model is available for local use through tools such as Transformers, ONNX Runtime, and compatible model-serving applications. Microsoft documents support across Windows, Linux, Mac desktops, and some mobile CPU deployments.
What license does Phi-3-mini-4k-instruct use?
The model is published under the MIT license. Its intended input is text, commonly formatted as a system, user, and assistant chat conversation.
explore Explore More
Similar to Phi-3-mini-4k-instruct
See all arrow_forward
Reviews & Comments
Write a Review
Be the first to review
Share your thoughts with the community and help others make better decisions.
