How to use from
llama.cppInstall 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:# Run inference directly in the terminal:
llama cli -hf FloatinggOnion/mobile-llm-quant-demo:Build from source code
git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf FloatinggOnion/mobile-llm-quant-demo:# Run inference directly in the terminal:
./build/bin/llama cli -hf FloatinggOnion/mobile-llm-quant-demo:Use Docker
docker model run hf.co/FloatinggOnion/mobile-llm-quant-demo:Quick Links
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
- 90
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf FloatinggOnion/mobile-llm-quant-demo:# Run inference directly in the terminal: llama cli -hf FloatinggOnion/mobile-llm-quant-demo: