Downloads · 30 days
105
100% of all-time downloads
stAvI-Vionano-V2
gleraTech/stAvI-Vionano-V2
stAvI-Vionano-V2 is a text generation model from gleraTech. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
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.
All-time downloads
105
Public
Parameters
1.7B
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors968 MB · 99%
Parameter types
How the weights are stored.
U321.7B · 100%
Base models
Model card
From the Hugging Face model README
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
- Task
- Text Generation
- Library
- mlx
- Type
- qwen3
- License
- apache-2.0
- Languages
- de, en
- Created
- Sep 14, 2026
- Updated
- Oct 2, 2026