How to use from
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 Vizuara/OpenFlow
# Run inference directly in the terminal:
llama cli -hf Vizuara/OpenFlow
Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Vizuara/OpenFlow
# Run inference directly in the terminal:
llama cli -hf Vizuara/OpenFlow
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 Vizuara/OpenFlow
# Run inference directly in the terminal:
./build/bin/llama cli -hf Vizuara/OpenFlow
Use Docker
docker model run hf.co/Vizuara/OpenFlow
Quick Links

OpenFlow downloads

OpenFlow is free voice typing from Vizuara: hold a key, speak, let go, and clean text appears in any app. Everything runs on your own device; your voice never leaves it.

Download from the website: https://rajatdandekar--openflow.modal.run (it picks the right file for your computer). This repository hosts the installers on Hugging Face's CDN so downloads are fast everywhere.

File For
OpenFlow-mac-applesilicon.dmg Mac with Apple silicon (M1 to M4), macOS 14+
OpenFlow-mac-universal.dmg Intel Macs and macOS 12-13
OpenFlow-Windows-x64.zip Windows 10/11, 64-bit
OpenFlow-Android.apk Android 9+, 64-bit

Check downloads against SHA256SUMS.txt. Models: NVIDIA Parakeet (CC-BY-4.0) and a Liquid AI LFM-based clean-up model fine-tuned on public and synthetic data (LFM Open License); see NOTICE in each app.

Downloads last month
209
GGUF
Model size
1B params
Architecture
lfm2
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support