Instructions to use Swicked86/phi4-mm-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Swicked86/phi4-mm-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Swicked86/phi4-mm-gguf",
	filename="mmproj-phi4-mm-f16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Swicked86/phi4-mm-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Swicked86/phi4-mm-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Swicked86/phi4-mm-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Swicked86/phi4-mm-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Swicked86/phi4-mm-gguf:Q4_K_M

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 Swicked86/phi4-mm-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Swicked86/phi4-mm-gguf:Q4_K_M

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 Swicked86/phi4-mm-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Swicked86/phi4-mm-gguf:Q4_K_M

Use Docker

docker model run hf.co/Swicked86/phi4-mm-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use Swicked86/phi4-mm-gguf with Ollama:
```
ollama run hf.co/Swicked86/phi4-mm-gguf:Q4_K_M
```

Unsloth Studio

How to use Swicked86/phi4-mm-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 Swicked86/phi4-mm-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 Swicked86/phi4-mm-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Swicked86/phi4-mm-gguf to start chatting

How to use Swicked86/phi4-mm-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Swicked86/phi4-mm-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Swicked86/phi4-mm-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Swicked86/phi4-mm-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Swicked86/phi4-mm-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Swicked86/phi4-mm-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Swicked86/phi4-mm-gguf with Docker Model Runner:
```
docker model run hf.co/Swicked86/phi4-mm-gguf:Q4_K_M
```

Lemonade

How to use Swicked86/phi4-mm-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Swicked86/phi4-mm-gguf:Q4_K_M

Run and chat with the model

lemonade run user.phi4-mm-gguf-Q4_K_M

List all available models

lemonade list

phi4-mm-gguf / deploy /README-deployment.md

Swicked86

Upload deploy/README-deployment.md with huggingface_hub

471bf5f verified 3 months ago

preview code

raw

history blame contribute delete

3.94 kB

metadata

license: mit
base_model: microsoft/Phi-4-multimodal-instruct
tags:
  - phi4mm
  - gguf
  - quantized
  - q4_k_m
  - cpu
  - ollama
  - llama-cpp
language:
  - multilingual
  - ar
  - zh
  - cs
  - da
  - nl
  - en
  - fi
  - fr
  - de
  - he
  - hu
  - it
  - ja
  - ko
  - 'no'
  - pl
  - pt
  - ru
  - es
  - sv
  - th
  - tr
  - uk
pipeline_tag: text-generation

Phi-4 Multimodal Instruct — GGUF Quantizations

CPU-optimised GGUF quantizations of microsoft/Phi-4-multimodal-instruct produced with llama.cpp.

Model Summary

Phi-4-multimodal-instruct is a 5.6 B parameter lightweight multimodal foundation model by Microsoft that processes text, image, and audio inputs. The backbone LLM is Phi-4-Mini (3.8 B). This repository contains GGUF quantizations for local CPU and GPU deployment.

Context length: 128 K tokens (131 072)
Architecture: phi3 (GGUF)

Available Files

File	Quant	Size	BPW	Best for
`phi4-mm-Q4_K_M.gguf`	Q4_K_M	2.37 GB	5.18	CPU inference, 8 GB RAM systems
`phi4-mm-Q8_0.gguf`	Q8_0	3.90 GB	8.00	GPU/high-RAM systems, near-lossless
`phi4-mm-f16.gguf`	F16	7.17 GB	16.00	Source / re-quantization base

Quantization Method

Quantized using llama-quantize from ggerganov/llama.cpp (build 8334).

llama-quantize phi4-mm-f16.gguf phi4-mm-Q4_K_M.gguf Q4_K_M 16

Source weights converted from the original safetensors using convert_hf_to_gguf.py.

Recommended Usage

Ollama (CPU — Intel NUC / low-power hardware)

# Pull and run (once uploaded to Ollama registry)
ollama run phi4-mm-nuc

# Or import from GGUF directly with a Modelfile:
ollama create phi4-mm-nuc -f Modelfile
ollama run phi4-mm-nuc

Modelfile for 8 GB RAM / no GPU:

FROM phi4-mm-Q4_K_M.gguf
PARAMETER num_ctx 8192
PARAMETER num_thread 8
PARAMETER num_gpu 0
PARAMETER flash_attn false
PARAMETER temperature 0.7
PARAMETER repeat_penalty 1.1
SYSTEM "You are a helpful, accurate, and concise AI assistant."

llama.cpp CLI (GPU, full quality)

./build/bin/llama-cli \
  -m phi4-mm-Q8_0.gguf \
  --ctx-size 65536 \
  --flash-attn on \
  --kv-offload \
  -ngl 99 \
  --threads 16

OpenClaw Integration

In ~/.openclaw/openclaw.json:

{
  "agent": {
    "model": "ollama/phi4-mm-nuc"
  },
  "modelConfigs": {
    "ollama/phi4-mm-nuc": {
      "provider": "ollama",
      "model": "phi4-mm-nuc",
      "baseUrl": "http://localhost:11434"
    }
  }
}

Hardware Notes

Hardware	Recommended quant	Context	Notes
Intel NUC 11th Gen, 8 GB RAM	Q4_K_M	8 192	CPU-only, `num_gpu 0`
Laptop / desktop, 16 GB RAM	Q5_K_M or Q8_0	16 384	CPU or iGPU
GPU with ≥ 8 GB VRAM	Q8_0 or F16	32 768–65 536	Full `-ngl 99` offload

License

This repository redistributes quantized weights derived from microsoft/Phi-4-multimodal-instruct under the original MIT License.

MIT License
Copyright (c) Microsoft Corporation.

Quantization tooling (llama.cpp) is also MIT licensed. See llama.cpp LICENSE.

Attribution

Original model: Microsoft Research
Quantization: produced with llama.cpp by Georgi Gerganov et al.
Technical report: arXiv:2503.01743