---
license: gemma
pipeline_tag: image-text-to-text
base_model: INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0
tags:
  - gemma3
  - uk
  - ukrainian
  - gguf
language:
  - uk
  - en
---

# MamayLM-Gemma-3-12B-IT-v2.0-GGUF

GGUF quantized versions of [MamayLM-Gemma-3-12B-IT-v2.0](https://huggingface.co/INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0) for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible tools. MamayLM v2.0 is a series of Ukrainian-adapted LLMs based on Gemma 3, developed by [INSAIT](https://insait.ai).

**Blog post**: [MamayLM v2.0 Release](https://models.mamay.ai/blog/mamaylm-v2-release-en/)

### Key improvements over MamayLM v1.0

1. **Vision-language understanding** — The model understands both text and images within the same context.
2. **Instruction-following** — Trained on a broader range of tasks, multi-turn conversations, complex instructions, and system prompts.
3. **Longer context** — Effective context of 131k tokens for longer conversations and complex instructions.
4. **Updated knowledge cut-off** — Pretraining data up to May 2025, instruction fine-tuning up to October 2025.

## Available quantizations

| Filename | Quant type | Description |
|----------|-----------|-------------|
| `MamayLM-Gemma-3-12B-IT-v2.0-Q4_K_M.gguf` | Q4_K_M | Good balance of quality and size — **recommended** |
| `MamayLM-Gemma-3-12B-IT-v2.0-Q5_K_M.gguf` | Q5_K_M | High quality, slightly larger |
| `MamayLM-Gemma-3-12B-IT-v2.0-Q6_K.gguf` | Q6_K | Very high quality, near lossless |
| `MamayLM-Gemma-3-12B-IT-v2.0-Q8_0.gguf` | Q8_0 | Essentially lossless |

## Usage

### llama.cpp

```bash
# Download a specific quantization
huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-GGUF \
    --include "MamayLM-Gemma-3-12B-IT-v2.0-Q4_K_M.gguf" \
    --local-dir .

# Run with llama-cli
llama-cli -m MamayLM-Gemma-3-12B-IT-v2.0-Q4_K_M.gguf \
    -p "Коли був заснований Київський університет?" \
    -n 512
```

### Ollama

Create a `Modelfile`:

```
FROM ./MamayLM-Gemma-3-12B-IT-v2.0-Q4_K_M.gguf
```

Then:

```bash
ollama create mamaylm-gemma3-12b-v2.0 -f Modelfile
ollama run mamaylm-gemma3-12b-v2.0
```

### LM Studio

Search for `MamayLM-Gemma-3-12B-IT-v2.0-GGUF` in the model browser, or download a GGUF file manually and load it.

## Download

```bash
# Download all quantizations
huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-GGUF

# Download a specific file
huggingface-cli download INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-GGUF \
    --include "MamayLM-Gemma-3-12B-IT-v2.0-Q4_K_M.gguf" \
    --local-dir .
```


## License

MamayLM-Gemma-3-12B-IT-v2.0-GGUF is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms).