Instructions to use hardwareai/telar-partes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use hardwareai/telar-partes 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 hardwareai/telar-partes:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hardwareai/telar-partes:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hardwareai/telar-partes:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf hardwareai/telar-partes: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 hardwareai/telar-partes:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf hardwareai/telar-partes:Q4_K_M

Use Docker

docker model run hf.co/hardwareai/telar-partes:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use hardwareai/telar-partes with Ollama:
```
ollama run hf.co/hardwareai/telar-partes:Q4_K_M
```
Unsloth Desktop

How to use hardwareai/telar-partes with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hardwareai/telar-partes: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": "hardwareai/telar-partes:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hardwareai/telar-partes with Docker Model Runner:
```
docker model run hf.co/hardwareai/telar-partes:Q4_K_M
```

Lemonade

How to use hardwareai/telar-partes with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hardwareai/telar-partes:Q4_K_M

Run and chat with the model

lemonade run user.telar-partes-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use hardwareai/telar-partes with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hardwareai/telar-partes: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 hardwareai/telar-partes:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hardwareai/telar-partes with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hardwareai/telar-partes: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 "hardwareai/telar-partes: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"

Partes de Telar

Las partes que la app Telar (HardwareAI) baja de internet, para instalar sin memoria USB. La app elige qué bajar y comprueba cada archivo con su huella SHA-256 antes de instalarlo; no hace falta bajarlas a mano.

Carpeta o archivo	Qué es	Licencia
`trenza-1-Q4_K_M.gguf`	Telar Trenza, el modelo del chat (5,0 GB)	Apache-2.0 (`LICENSE`, avisos en `NOTICE.md`)
`dictado/`	El modelo del dictado y la conversación por voz (190 MB)	MIT
`vision/`	Lectura de imágenes: fotos y PDF escaneados (3,0 GB)	Apache-2.0
`telefono/`	El modelo que la app copia al teléfono (2,5 GB)	MIT (`telefono/LICENSE-phi-4-mini.txt`)
`aguja.zip`	Compilar firmware para ESP32 (arduino-cli y el core esp32)	GPL-3.0 y las de cada herramienta, dentro del zip

Cada carpeta trae su SHA256SUMS.txt.

Downloads last month: 81

GGUF

Model size

8B params

Architecture

qwen3

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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