---
license: apache-2.0
base_model:
- mistralai/Devstral-Small-2-24B-Instruct-2512
tags:
- mistralai
- devstral
- devstral-small
- gguf
- llama.cpp
- text-generation
- quantized
---

# Devstral-Small-2-24B-Instruct-2512-GGUF

This repository provides a **GGUF conversion** of  
[mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512).

The model is intended for **local inference** using the llama.cpp ecosystem and compatible tools.

---

## Model Details

- **Base model**: mistralai/Devstral-Small-2-24B-Instruct-2512  
- **Parameters**: 24B  
- **Format**: GGUF (F16)  
- **Task**: Text Generation  
- **Fine-tuning**: None (direct conversion)

---

## Relationship to the base model

This model is a **format conversion only**.  
No additional training, fine-tuning, or alignment steps were applied.

All weights originate from the original model published by Mistral AI.

---

## Usage (llama.cpp)

```bash
./llama-cli \
  -m Devstral-Small-2-24B-Instruct-2512.gguf \
  -p "Your prompt here"