Instructions to use Fendrix-Studio/Stera-AI-Lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Fendrix-Studio/Stera-AI-Lite 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 Fendrix-Studio/Stera-AI-Lite:F16
# Run inference directly in the terminal:
llama cli -hf Fendrix-Studio/Stera-AI-Lite:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Fendrix-Studio/Stera-AI-Lite:F16
# Run inference directly in the terminal:
llama cli -hf Fendrix-Studio/Stera-AI-Lite:F16

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 Fendrix-Studio/Stera-AI-Lite:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf Fendrix-Studio/Stera-AI-Lite:F16

Use Docker

docker model run hf.co/Fendrix-Studio/Stera-AI-Lite:F16

Llama new
LM Studio
Jan
Ollama
How to use Fendrix-Studio/Stera-AI-Lite with Ollama:
```
ollama run hf.co/Fendrix-Studio/Stera-AI-Lite:F16
```
Unsloth Desktop

How to use Fendrix-Studio/Stera-AI-Lite with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fendrix-Studio/Stera-AI-Lite:F16

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": "Fendrix-Studio/Stera-AI-Lite:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Fendrix-Studio/Stera-AI-Lite with Docker Model Runner:
```
docker model run hf.co/Fendrix-Studio/Stera-AI-Lite:F16
```

Lemonade

How to use Fendrix-Studio/Stera-AI-Lite with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fendrix-Studio/Stera-AI-Lite:F16

Run and chat with the model

lemonade run user.Stera-AI-Lite-F16

List all available models

lemonade list

Hermes Agent

How to use Fendrix-Studio/Stera-AI-Lite with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fendrix-Studio/Stera-AI-Lite:F16

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 Fendrix-Studio/Stera-AI-Lite:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Fendrix-Studio/Stera-AI-Lite with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Fendrix-Studio/Stera-AI-Lite:F16

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 "Fendrix-Studio/Stera-AI-Lite:F16" \
  --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"

Stera AI Lite V14

Personal multimodal (Vision-Language) model trained and developed by Fendrix Studio (Latest version: November 1, 2026).

Included Files

model-Stera-Lite-Q4_K_M.gguf: Main language model quantized in Q4_K_M format for an excellent performance-to-memory ratio.
mmproj-Stera-Lite_F16.gguf: Vision projector in F16 format, required to enable image analysis and multimodal capabilities.

Base Model

Architecture: Based on Qwen/Qwen3.5-2B

Usage

Open your Stera AI application.
Download and install the Stera-AI-Lite-V14 model.
Launch execution to interact with the model using text and vision inputs.

Evaluated Performance Benchmarks

Here is the estimated comparative performance of Stera-AI-Lite against current major architectures on complex agentic coding and autonomous agent behavior tasks.

Metric / Benchmark	Stera-AI-Lite	Qwen3.7-Plus	DeepSeek-V4-Flash	Claude-Opus-4.6
Coding
Agentic coding DeepSWE 1.1	24.5	16.5	54.4	--
Agentic coding SWE-bench Pro	31.2	55.8	56.0	53.4
Multilingual software engineering SWE-bench Multilingual	42.8	75.8	--	77.5
Repo-level code generation NL2Repo-Bench	28.7	41.1	54.2	47.6
Agent
Long-horizon office work CoWorkBench	39.5	65.1	45.1	68.2
Professional job tasks JobBench	21.3	27.6	41.3	36.6
Frontier agentic tasks Agents' Last Exam (Score)	23.1	33.6	--	--
Real-world tool use Toolathlon Verified	44.0	50.6	70.3	--

Developed with passion in France. Non-profit organization ❤️🚀.

Downloads last month: 128

GGUF

Model size

4B params

Architecture

qwen3vl

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for Fendrix-Studio/Stera-AI-Lite

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Quantized

(318)

this model