MediPhi-Instruct-GGUF

MediPhi-Instruct GGUF

GGUF versions of MediPhi-Instruct prepared for local inference.

This repository provides both an F16 version and a Q4_K_M quantized version for use with llama.cpp and other GGUF-compatible inference engines.

Available Files

Recommended Version

MediPhi-Instruct-Q4_K_M.gguf is recommended for most local inference setups because it requires substantially less memory than the F16 version.

The F16 version is provided when higher precision is preferred and sufficient memory is available.

Quantization

The Q4_K_M file was generated from the F16 GGUF model using the quantization tools provided by llama.cpp.

Quantization format:

Q4_K_M

llama.cpp

Basic usage:

llama-cli -m MediPhi-Instruct-Q4_K_M.gguf

GPU offloading:

llama-cli -m MediPhi-Instruct-Q4_K_M.gguf -ngl 99

Local server:

llama-server -m MediPhi-Instruct-Q4_K_M.gguf -ngl 99

Compatible Software

• llama.cpp
• llama-cpp-python
• LM Studio
• Jan
• Other GGUF-compatible runtimes

Original Model

This repository contains a community GGUF conversion and quantization of MediPhi-Instruct.

Original model:

PLACE_ORIGINAL_MODEL_URL_HERE

Please refer to the original model repository for the model license, intended use, limitations, and attribution requirements.

Disclaimer

This repository is not an official repository of the original model authors unless explicitly stated.

SHA256

Checksums can be generated with:

sha256sum *.gguf