Instructions to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
llama cli -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
llama cli -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
./llama-cli -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
# Run inference directly in the terminal:
./build/bin/llama-cli -hf exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Use Docker

docker model run hf.co/exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

LM Studio
Jan

vLLM

How to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Ollama
How to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with Ollama:
```
ollama run hf.co/exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
```
Unsloth Desktop
Docker Model Runner
How to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with Docker Model Runner:
```
docker model run hf.co/exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers
```

Lemonade

How to use exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Run and chat with the model

lemonade run user.Phi-4-reasoning-plus-UD-Q4_K_XL-layers-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Original Model Link : unsloth/Phi-4-reasoning-plus-GGUF

name: Phi-4-reasoning-plus-UD-Q4_K_M-layers
description: > 
 split-layer format for distributed serving via mesh-llm
base_model: microsoft/phi-4
license: mit
library_name: llama.cpp
pipeline_tag: text-generation
tasks: text-generation
tags:
- mesh-llm
- microsoft
- phi-4
- unsloth
- distributed
language: en
license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE
get_started_code: mesh-llm serve --model "exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers" --split

Downloads last month: 608

GGUF

Model size

0.3B params

Architecture

phi3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for exdysa/Phi-4-reasoning-plus-UD-Q4_K_XL-layers

Base model

microsoft/phi-4

Quantized

(167)

this model