Instructions to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF",
	filename="phi-4-reasoning-vision-15b-q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

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 gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

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 gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

Ollama
How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with Ollama:
```
ollama run hf.co/gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF to start chatting

Docker Model Runner
How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0
```

Lemonade

How to use gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Phi-4-reasoning-vision-15B-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Phi-4-reasoning-vision-15B-Q8_0-GGUF / README.md

gaoqianshen

Upload README.md with huggingface_hub

e58ac95 verified about 2 months ago

preview code

raw

history blame contribute delete

3.02 kB

metadata

license: mit
language:
  - en
tags:
  - multimodal
  - vision-language
  - reasoning
  - math
  - ocr
  - gui-grounding
  - computer-use
  - chain-of-thought
  - llama-cpp
  - gguf-my-repo
base_model: microsoft/Phi-4-reasoning-vision-15B
pipeline_tag: image-text-to-text
model-index:
  - name: Phi-4-Reasoning-Vision-15B
    results:
      - task:
          type: visual-question-answering
        dataset:
          name: AI2D
          type: ai2d
        metrics:
          - type: accuracy
            value: 84.8
      - task:
          type: visual-question-answering
        dataset:
          name: ChartQA
          type: chartqa
        metrics:
          - type: accuracy
            value: 83.3
      - task:
          type: visual-question-answering
        dataset:
          name: MathVista (MINI)
          type: mathvista
        metrics:
          - type: accuracy
            value: 75.2
      - task:
          type: visual-question-answering
        dataset:
          name: MMMU
          type: mmmu
        metrics:
          - type: accuracy
            value: 54.3
      - task:
          type: visual-question-answering
        dataset:
          name: OCRBench
          type: ocrbench
        metrics:
          - type: accuracy
            value: 76
      - task:
          type: visual-question-answering
        dataset:
          name: ScreenSpot-V2
          type: screenspot-v2
        metrics:
          - type: accuracy
            value: 88.2

gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF

This model was converted to GGUF format from microsoft/Phi-4-reasoning-vision-15B using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF --hf-file phi-4-reasoning-vision-15b-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF --hf-file phi-4-reasoning-vision-15b-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF --hf-file phi-4-reasoning-vision-15b-q8_0.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo gaoqianshen/Phi-4-reasoning-vision-15B-Q8_0-GGUF --hf-file phi-4-reasoning-vision-15b-q8_0.gguf -c 2048