Instructions to use lmstudio-community/phi-4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmstudio-community/phi-4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lmstudio-community/phi-4-GGUF",
	filename="phi-4-Q3_K_L.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lmstudio-community/phi-4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lmstudio-community/phi-4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lmstudio-community/phi-4-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 lmstudio-community/phi-4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lmstudio-community/phi-4-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 lmstudio-community/phi-4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lmstudio-community/phi-4-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 lmstudio-community/phi-4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmstudio-community/phi-4-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lmstudio-community/phi-4-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lmstudio-community/phi-4-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lmstudio-community/phi-4-GGUF:Q4_K_M

Ollama
How to use lmstudio-community/phi-4-GGUF with Ollama:
```
ollama run hf.co/lmstudio-community/phi-4-GGUF:Q4_K_M
```

Unsloth Studio

How to use lmstudio-community/phi-4-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 lmstudio-community/phi-4-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 lmstudio-community/phi-4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lmstudio-community/phi-4-GGUF to start chatting

Docker Model Runner
How to use lmstudio-community/phi-4-GGUF with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/phi-4-GGUF:Q4_K_M
```

Lemonade

How to use lmstudio-community/phi-4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmstudio-community/phi-4-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.phi-4-GGUF-Q4_K_M

List all available models

lemonade list

(Exit code: -1073740791). Unknown error. Try a different model and/or config

by michabbb - opened Jan 8, 2025

Discussion

michabbb

Jan 8, 2025

•

edited Jan 8, 2025

lmstudio-community/phi-4-GGUF/phi-4-Q4_K_M.gguf
lmstudio-community/phi-4-GGUF/phi-4-Q6_K.gguf

{
  "cause": "(Exit code: -1073740791). Unknown error. Try a different model and/or config.",
  "suggestion": "",
  "data": {
    "memory": {
      "ram_capacity": "63.65 GB",
      "ram_unused": "17.95 GB"
    },
    "gpu": {
      "gpu_names": [
        "NVIDIA GeForce RTX 4090 Laptop GPU"
      ],
      "vram_recommended_capacity": "15.99 GB",
      "vram_unused": "14.70 GB"
    },
    "os": {
      "platform": "win32",
      "version": "10.0.22631"
    },
    "app": {
      "version": "0.2.31",
      "downloadsDir": "D:\\LLM"
    },
    "model": {}
  },
  "title": "Error loading model."
}

hi there, can someone help me here ? i don´t know what´s wrong here... thanks !

mantafloppy

Jan 9, 2025

•

edited Jan 9, 2025

EDIT
NVM, its says its not compatible yet on Bartowski:

Run them in LM Studio with version 0.3.6

Ollama doesn't yet support this (as of January 8 2025)

Broken on Ollama also :

~ % ollama run hf.co/lmstudio-community/phi-4-GGUF:Q8_0
pulling manifest 
pulling f44fdfa30b19... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  15 GB                         
pulling 1ae29500b4be... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  206 B                         
pulling 914cdee286e1... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  162 B                         
pulling 8aacca6925b2... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  191 B                         
verifying sha256 digest 
writing manifest 
success 
Error: llama runner process has terminated: GGML_ASSERT(hparams.n_swa > 0) failed

Seem original is broken too...

~ % ollama run hf.co/bartowski/phi-4-GGUF:Q8_0
pulling manifest 
pulling c4babb4b4d87... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  15 GB                         
pulling 1ae29500b4be... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  206 B                         
pulling 914cdee286e1... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  162 B                         
pulling 8aacca6925b2... 100% ▕██████████████████████████████████████████████████████████████████████████████████████▏  191 B                         
verifying sha256 digest 
writing manifest 
success 
Error: llama runner process has terminated: GGML_ASSERT(hparams.n_swa > 0) failed
~ %

yagilb

LM Studio Community org Jan 9, 2025

Hey all: you need the newest engines in LM Studio for this to work. The easiest way to get them is installing LM Studio 0.3.6 from https://lmstudio.ai/download

michabbb

Jan 9, 2025

oh shit... my lmstuido was so old, that even the "update" check didn´t show any new updates... i am not on the latest version and that model is working 🤗

michabbb changed discussion status to closed Jan 9, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment