Instructions to use kstorm77/meloa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use kstorm77/meloa 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 kstorm77/meloa:Q4_K_M # Run inference directly in the terminal: llama cli -hf kstorm77/meloa:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf kstorm77/meloa:Q4_K_M # Run inference directly in the terminal: llama cli -hf kstorm77/meloa: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 kstorm77/meloa:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf kstorm77/meloa: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 kstorm77/meloa:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf kstorm77/meloa:Q4_K_M
Use Docker
docker model run hf.co/kstorm77/meloa:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use kstorm77/meloa with Ollama:
ollama run hf.co/kstorm77/meloa:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use kstorm77/meloa with Docker Model Runner:
docker model run hf.co/kstorm77/meloa:Q4_K_M
- Lemonade
How to use kstorm77/meloa with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kstorm77/meloa:Q4_K_M
Run and chat with the model
lemonade run user.meloa-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Meloa models
Every model the Meloa apps download, in one place. Each folder holds one model's files unchanged from the source it names, its licence and notice files, and a README with each file's size and SHA-256. The apps check every file against that SHA-256 before using it.
| Folder | Used for | Licence |
|---|---|---|
english/parakeet-tdt-0.6b-v2/ |
English transcription on computers with a lower score. | CC BY 4.0 |
english/granite-speech-4.1-2b/ |
English transcription on computers with a higher score. | Apache-2.0 |
danish/whisper-small-danish/ |
Danish transcription on computers with a lower score. | MIT |
danish/edda-v0.2/ |
Danish transcription on computers with a higher score. | Apache-2.0 |
language-detection/sherpa-onnx-whisper-base/ |
Telling which language a meeting is in, on computers. | MIT or Apache-2.0 |
language-detection/whisper-base-q5_1/ |
Telling which language a meeting is in, on phones. | MIT or Apache-2.0 |
speakers/pyannote-segmentation-3.0/ |
Finding where each speaker talks, on computers. | MIT |
speakers/titanet-small/ |
Telling speakers apart by their voice, on computers. | Apache-2.0 |
other-languages/whisper-large-v3/ |
Transcription in every language other than Danish and English, on computers. | MIT or Apache-2.0 |
phone/whisper-small-q5_1/ |
Transcription on the phone itself. | MIT or Apache-2.0 |
notes/qwen3.5-4b/ |
Writing the meeting notes, on computers. | Apache-2.0 |
Each model keeps its own licence; see the folder's LICENSE files and README. Nothing in this repository
is licensed by Meloa itself.
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
4-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support