Instructions to use FloatinggOnion/mobile-llm-quant-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FloatinggOnion/mobile-llm-quant-demo with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FloatinggOnion/mobile-llm-quant-demo",
	filename="gemma/gemma-IQ3_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FloatinggOnion/mobile-llm-quant-demo 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 FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FloatinggOnion/mobile-llm-quant-demo:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FloatinggOnion/mobile-llm-quant-demo: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 FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FloatinggOnion/mobile-llm-quant-demo: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 FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FloatinggOnion/mobile-llm-quant-demo:Q4_K_M

Use Docker

docker model run hf.co/FloatinggOnion/mobile-llm-quant-demo:Q4_K_M

LM Studio
Jan
Ollama
How to use FloatinggOnion/mobile-llm-quant-demo with Ollama:
```
ollama run hf.co/FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
```

Unsloth Studio

How to use FloatinggOnion/mobile-llm-quant-demo 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 FloatinggOnion/mobile-llm-quant-demo 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 FloatinggOnion/mobile-llm-quant-demo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FloatinggOnion/mobile-llm-quant-demo to start chatting

Atomic Chat new
Docker Model Runner
How to use FloatinggOnion/mobile-llm-quant-demo with Docker Model Runner:
```
docker model run hf.co/FloatinggOnion/mobile-llm-quant-demo:Q4_K_M
```

Lemonade

How to use FloatinggOnion/mobile-llm-quant-demo with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FloatinggOnion/mobile-llm-quant-demo:Q4_K_M

Run and chat with the model

lemonade run user.mobile-llm-quant-demo-Q4_K_M

List all available models

lemonade list

Mobile Quantization Demo Models

This repository contains GGUF quantizations optimized for laptop and mobile deployment.

Models Included

Qwen 3.5 0.8B (Standard Q4_K_M + Calibrated IQ3_M)
Gemma 3 E2B IT (Standard Q4_K_M + Calibrated IQ3_M)

Calibration

These models were quantized using Importance Matrix (IMatrix) calibration with the WikiText dataset to preserve accuracy at low bit-widths (IQ3).

Usage

llama-cli -m qwen-IQ3_M.gguf -p "Explain quantum physics" -n 128

Downloads last month: 125

GGUF

Model size

4B params

Architecture

gemma3n

Hardware compatibility

3-bit

4-bit

16-bit

Inference Providers NEW

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