Instructions to use admintyne/tyne-core-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use admintyne/tyne-core-models 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 admintyne/tyne-core-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf admintyne/tyne-core-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf admintyne/tyne-core-models:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf admintyne/tyne-core-models:Q4_K_M

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 admintyne/tyne-core-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf admintyne/tyne-core-models:Q4_K_M

Use Docker

docker model run hf.co/admintyne/tyne-core-models:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use admintyne/tyne-core-models with Ollama:
```
ollama run hf.co/admintyne/tyne-core-models:Q4_K_M
```
Unsloth Desktop

How to use admintyne/tyne-core-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf admintyne/tyne-core-models:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "admintyne/tyne-core-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use admintyne/tyne-core-models with Docker Model Runner:
```
docker model run hf.co/admintyne/tyne-core-models:Q4_K_M
```

Lemonade

How to use admintyne/tyne-core-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull admintyne/tyne-core-models:Q4_K_M

Run and chat with the model

lemonade run user.tyne-core-models-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use admintyne/tyne-core-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf admintyne/tyne-core-models:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default admintyne/tyne-core-models:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use admintyne/tyne-core-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf admintyne/tyne-core-models:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "admintyne/tyne-core-models:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Tyne on-device model catalog

Public, versioned model artifacts used by the Tyne macOS app. Tyne downloads these files during onboarding and runs them locally; user audio, prompts, and documents are not sent to these models over the network.

Current catalog

Tyne feature	Artifact path	Upstream source	License
Loom 3B local assistant	`loom-3b/ministral-3-3b-instruct-2512-q4_k_m.gguf`	`mistralai/Ministral-3-3B-Instruct-2512-GGUF`	Apache-2.0
S1-mini text normalization	`s1-mini/s1-mini-q4_k_m.gguf`	`superwhisper/s1-mini-GGUF`	Upstream custom terms (Apache-2.0 plus naming requirement)
Parakeet dictation	`parakeet-tdt-0.6b-v2-coreml/`	`FluidInference/parakeet-tdt-0.6b-v2-coreml`	CC-BY-4.0
Whisper meeting transcription	`openai_whisper-large-v3-v20240930_turbo_632MB/`	`argmaxinc/whisperkit-coreml`	MIT
Speaker diarization	`speaker_segmenter/`, `speaker_embedder/`, `speaker_clusterer/`	`argmaxinc/speakerkit-coreml`	CC-BY-4.0

CURRENT_SHA256SUMS contains a checksum for every current file and CURRENT_DOWNLOAD_URLS.txt contains direct public download URLs. Historical Loom 4B, Moonshine, and prefixed Whisper paths remain in this repository so old Tyne builds are not broken.

Attribution

The files remain subject to their upstream licenses and model cards. This repository is a distribution mirror for Tyne and does not claim authorship of the upstream models. S1-mini must retain the name S1-mini by Superwhisper.

Downloads last month: 13

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

4-bit

Inference Providers NEW

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