This repository hosts GGUF quantized versions of Microsoft's Phi-3.5-mini-instruct model. It provides multiple quantization levels (IQ, Q2_K through Q4) for efficient local inference using tools like llama.cpp. The model supports instruction following and is optimized for on-device or CPU/GPU usage without requiring cloud APIs.
Phi 3.5 Mini Instruct is a Text generation project. It focuses on running the Phi-3.5-mini language model efficiently on consumer hardware using quantized GGUF format. It is built as an open-source project for developers and AI enthusiasts. Phi 3.5 Mini Instruct is open source under the MIT license. It runs on the web, the command line, and API.
Behind Phi 3.5 Mini Instruct is bartowski, and it first shipped in 2023. The project is developed in the open on GitHub with 121.2k stars and 1.2k commits in the last 90 days. Key capabilities include GGUF Quantization, Local Inference, and Chat Template. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do