# DeepSeek-V3.2 Arrives With FP8 Weights, MIT License

> The new Mixture-of-Experts model from DeepSeek AI combines an efficient FP8 architecture with a fully permissive license for commercial use.

Published by The Open Weights on Dec 1, 2025. Canonical: https://theopenweights.com/news/deepseek-v3-2-8ghv

## Key facts

- Company: DeepSeek
- Model: DeepSeek-V3.2
- Version: V3.2
- Category: Text / LLM
- Modalities: Text / LLM
- License: MIT (Open weights, commercial use allowed)
- Context window: 164K tokens
- Architecture: DeepseekV32ForCausalLM
- Precision: FP8
- Weights size: 689.3 GB
- Significance: notable
- Published: 2025-12-01
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V3.2
- Canonical URL: https://theopenweights.com/news/deepseek-v3-2-8ghv

DeepSeek AI has released DeepSeek-V3.2, a new open-source language model that stands out for its technical efficiency and permissive licensing. The model uses a Mixture-of-Experts (MoE) architecture, placing it among a class of powerful yet computationally lean models designed for scalable inference.

The most notable technical feature is its use of FP8 (8-bit floating point) weights. This precision format significantly reduces the model's memory footprint compared to traditional 16-bit models. For developers, this translates to faster inference and the ability to run the model on more accessible, consumer-grade hardware.

The MoE design complements this focus on efficiency. By routing input tokens to specialized "expert" sub-networks, the model can achieve the performance of a much larger dense model while only activating a fraction of its parameters for any given task, further reducing computational costs.

Perhaps most importantly for the open-source community, DeepSeek-V3.2 is available under the [MIT License](https://huggingface.co/deepseek-ai/DeepSeek-V3.2). This choice removes many of the commercial use restrictions seen with other high-performance models, offering developers and businesses a truly open foundation for building new applications.

## Get the model

- [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V3.2)

## Sources

- [deepseek-ai/DeepSeek-V3.2](https://huggingface.co/deepseek-ai/DeepSeek-V3.2) — Hugging Face, Dec 1, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "DeepSeek-V3.2 Arrives With FP8 Weights, MIT License", The Open Weights, Dec 1, 2025, https://theopenweights.com/news/deepseek-v3-2-8ghv