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

This repository provides a GGUF conversion of
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)

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