Instructions to use nzgnzg73/llama_cpp_WebUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nzgnzg73/llama_cpp_WebUI with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="nzgnzg73/llama_cpp_WebUI",
	filename="Image-Text-to-Text Models/gemma-3/gemma-3-12b-it-Q4_K_S.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 nzgnzg73/llama_cpp_WebUI with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S
# Run inference directly in the terminal:
llama-cli -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S

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 nzgnzg73/llama_cpp_WebUI:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S

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 nzgnzg73/llama_cpp_WebUI:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nzgnzg73/llama_cpp_WebUI:Q4_K_S

Use Docker

docker model run hf.co/nzgnzg73/llama_cpp_WebUI:Q4_K_S

LM Studio
Jan
Ollama
How to use nzgnzg73/llama_cpp_WebUI with Ollama:
```
ollama run hf.co/nzgnzg73/llama_cpp_WebUI:Q4_K_S
```

Unsloth Studio new

How to use nzgnzg73/llama_cpp_WebUI 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 nzgnzg73/llama_cpp_WebUI 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 nzgnzg73/llama_cpp_WebUI to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nzgnzg73/llama_cpp_WebUI to start chatting

Docker Model Runner
How to use nzgnzg73/llama_cpp_WebUI with Docker Model Runner:
```
docker model run hf.co/nzgnzg73/llama_cpp_WebUI:Q4_K_S
```

Lemonade

How to use nzgnzg73/llama_cpp_WebUI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nzgnzg73/llama_cpp_WebUI:Q4_K_S

Run and chat with the model

lemonade run user.llama_cpp_WebUI-Q4_K_S

List all available models

lemonade list

nzgnzg73

llama_cpp_WebUI

Github https://github.com/nzgnzg73/llama_cpp_WebUI

Want to talk or ask something?

Just click the YouTube link below! You'll find my 📧 email there and can message me easily. 👇

🎥 YouTube Channel: @nzg73 🔗 https://youtube.com/@NZG73

Contact Email 👇👇👀

E-mail:- nzgnzg73@gmail.com

llama Cpp (cp\gpu) Old Version llama cpp 👇👇👇👇 llama-b7200-bin-win-cpu-x64.zip

NEW Update Version llama cpp 👇👇👇👇

llama-b7541-bin-win-cpu-x64

llama-b7243-bin-win-cuda-12.4-x64

Llama Model Switcher

CMD model_switcher.py

pip install flask

pip install flask psutil GPUtil

Image-Text-to-Text Models

Gemma-3

CPU. RAM 20GB OR GPU. 4 VRAM

gemma-3-12b-it-Q4_K_S.gguf
mmproj-model-f16-12B.gguf

-Text-to-Text Models

GPT OSS 20

Qwen3

CPU. RAM 25GB OR GPU. 4 VRAM

Qwen3-VL-2B-Instruct-Q8_0.gguf
mmproj-Qwen3-VL-2B-Instruct-Q8_0.gguf

Qwen2.5-Omni

CPU. RAM 40GB OR GPU. 8 VRAM

Qwen2.5-Omni-7B-BF16.gguf
mmproj-F16.gguf 2GB

Audio-Text-to-Text

Llama-3.2

CPU. RAM 10GB

Llama-3.2-1B-Instruct-Q4_K_M.gguf
Llama-3.2-1B-Instruct-Q8_0.gguf
mmproj-ultravox-v0_5-llama-3_2-1b-f16.gguf

run.bat

Local Server

llama-server.exe --n-gpu-layers 2 --ctx-size 111192 -m ".\models\mistralai\mistralai_Voxtral-Mini-3B-2507-Q8_0.gguf" --mmproj ".\models\mistralai\mmproj-mistralai_Voxtral-Mini-3B-2507-bf16.gguf" --host 0.0.0.0 --port 8005

public URL

llama-server --n-gpu-layers 15 --ctx-size 8192 -m models/ollma/Llama-3.2-1B-Instruct-Q8_0.gguf --mmproj models/ollma/mmproj-ultravox-v0_5-llama-3_2-1b-f16.gguf --host 127.0.0.1 --port 8083

Downloads last month: 47

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support