---

base_model: TeichAI/Devstral-Small-2505-Deepseek-V3.2-Speciale-Distill tags:

• llama.cpp
• gguf
• unsloth

language:

• en

datasets:

• TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k
• TeichAI/deepseek-v3.2-speciale-1000x
• TeichAI/deepseek-v3.2-speciale-openr1-math-3k

---

Devstral Small 2505 - Deepseek v3.2 Speciale Distill

This model was trained on a non-reasoning (reasoning traces were removed) dataset of DeepSeek v3.2 Speciale.

• 🧬 Datasets:

- TeichAI/deepseek-v3.2-speciale-OpenCodeReasoning-3k - TeichAI/deepseek-v3.2-speciale-1000x - TeichAI/deepseek-v3.2-speciale-openr1-math-3k

• 🏗 Base Model:

- unsloth/Devstral-Small-2505

• ⚡ Use cases:

- Coding - Math - Chat - Deep Research

---