Instructions to use gleraTech/stAvI-Vionano-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gleraTech/stAvI-Vionano-V2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("gleraTech/stAvI-Vionano-V2")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use gleraTech/stAvI-Vionano-V2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gleraTech/stAvI-Vionano-V2"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "gleraTech/stAvI-Vionano-V2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use gleraTech/stAvI-Vionano-V2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "gleraTech/stAvI-Vionano-V2"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "gleraTech/stAvI-Vionano-V2"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "gleraTech/stAvI-Vionano-V2",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use gleraTech/stAvI-Vionano-V2 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gleraTech/stAvI-Vionano-V2"

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 gleraTech/stAvI-Vionano-V2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use gleraTech/stAvI-Vionano-V2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "gleraTech/stAvI-Vionano-V2"

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 "gleraTech/stAvI-Vionano-V2" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

stAvI Vionano — MLX

The built-in offline assistant of the stAvI iOS app by gleraTech solutions Austria GmbH. It runs entirely on-device and takes over automatically whenever the cloud model is unreachable.

Choose your format

stAvI Vionano ships in two formats, one repository each:

	MLX (this repo)	GGUF
Repository	`gleraTech/stAvI-Vionano-V2` ← you are here	`gleraTech/stAvI-Vionano-V2-GGUF`
Weights	`model.safetensors`	`stAvI-Vionano-v2.Q4_K_S.gguf`
Quantization	MLX 4-bit affine, group size 64	GGUF Q4_K_S
Runs on	Apple Silicon — macOS / iOS	llama.cpp, Ollama, LM Studio, Jan, Docker…
Load with	`mlx_lm`	`llama.cpp`, `ollama`

Download

# MLX — this repository
hf download gleraTech/stAvI-Vionano-V2

# GGUF — sibling repository
hf download gleraTech/stAvI-Vionano-V2-GGUF

Run it (MLX)

pip install mlx-lm

mlx_lm.generate \
  --model gleraTech/stAvI-Vionano-V2 \
  --prompt "Hallo, wer bist du?"

Model Details

Base model: Qwen/Qwen3-1.7B
Finetuning: Unsloth, 4000+ examples, custom stAvI dataset
Format: Apple MLX (4-bit) — the GGUF release is in gleraTech/stAvI-Vionano-V2-GGUF
Languages: German, English

Response Format

<response>
  <thinking>
    Internal reasoning here.
  </thinking>
  <answer>
    Answer here.
  </answer>
</response>

Credits

Qwen Team for Qwen3-1.7B
Unsloth for fast finetuning
gleraTech solutions Austria GmbH for finetuning

License

Apache 2.0

Downloads last month: 108

Safetensors

Model size

2B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for gleraTech/stAvI-Vionano-V2

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(418)

this model