deepseek-ai/DeepSeek-V3.2 · Hugging Face
huggingface.co
We’re on a journey to advance and democratize artificial intelligence through open source and open science.

DeepSeek has released V3.2, replacing the experimental version. There are two main models are open as always and can be downloaded from Hugging Face:

  • V3.2: General-purpose, balanced performance (GPT‑5 level)
  • V3.2‑Speciale: Specialized for complex reasoning (Gemini‑3.0‑Pro level)

V3.2 can now “think” while using tools (like searching the web, running code, or calling APIs). This makes AI assistants more transparent and better at multi‑step tasks. You can choose thinking mode (slower but more thorough) or non‑thinking mode (faster for simple tasks).

Key improvements are better reasoning transparency with the model explaining the steps when using tools, and stronger performance on benchmarks.