Instructions to use SableAI-Dev/Hugo-Lumen-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SableAI-Dev/Hugo-Lumen-1.0 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 SableAI-Dev/Hugo-Lumen-1.0
# Run inference directly in the terminal:
llama cli -hf SableAI-Dev/Hugo-Lumen-1.0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SableAI-Dev/Hugo-Lumen-1.0
# Run inference directly in the terminal:
llama cli -hf SableAI-Dev/Hugo-Lumen-1.0

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 SableAI-Dev/Hugo-Lumen-1.0
# Run inference directly in the terminal:
./llama-cli -hf SableAI-Dev/Hugo-Lumen-1.0

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 SableAI-Dev/Hugo-Lumen-1.0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SableAI-Dev/Hugo-Lumen-1.0

Use Docker

docker model run hf.co/SableAI-Dev/Hugo-Lumen-1.0

LM Studio
Jan
Ollama
How to use SableAI-Dev/Hugo-Lumen-1.0 with Ollama:
```
ollama run hf.co/SableAI-Dev/Hugo-Lumen-1.0
```
Unsloth Desktop

How to use SableAI-Dev/Hugo-Lumen-1.0 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SableAI-Dev/Hugo-Lumen-1.0

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": "SableAI-Dev/Hugo-Lumen-1.0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SableAI-Dev/Hugo-Lumen-1.0 with Docker Model Runner:
```
docker model run hf.co/SableAI-Dev/Hugo-Lumen-1.0
```

Lemonade

How to use SableAI-Dev/Hugo-Lumen-1.0 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SableAI-Dev/Hugo-Lumen-1.0

Run and chat with the model

lemonade run user.Hugo-Lumen-1.0-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use SableAI-Dev/Hugo-Lumen-1.0 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SableAI-Dev/Hugo-Lumen-1.0

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 SableAI-Dev/Hugo-Lumen-1.0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SableAI-Dev/Hugo-Lumen-1.0 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SableAI-Dev/Hugo-Lumen-1.0

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 "SableAI-Dev/Hugo-Lumen-1.0" \
  --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"

SableAI Lumen

Lumen is a fine-tuned version of Qwen 3.8-27B optimized for code generation and debugging.

Model Details

Base Model: Qwen 3.8-27B
Format: GGUF (4-bit quantized)
Size: 24GB
Language: Russian + English

Usage

Using llama-cpp-python

from llama_cpp import Llama

model = Llama( model_path="SableAI-Hugo-Lumen1.0.gguf", n_gpu_layers=-1, n_ctx=4096 )

response = model( "Write a Python function to sort a list", max_tokens=1024 ) print(response["choices"][0]["text"])

Performance

Tested on coding tasks and debugging scenarios. Better than GigaCode on Russian code tasks.

Limitations

Primarily trained for programming tasks
May struggle with very long contexts
Community feedback welcome

Downloads last month: 177

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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