---
title: "DeepSeek Quietly Drops V3-0324 With MIT License and 20-Point Math Jump"
subtitle: "DeepSeek quietly drops a major V3 update with near-reasoning-model math scores, MIT license, and 1M+ downloads on Hugging Face"
url: "https://alphasignal.ai/news/deepseek-quietly-drops-v3-0324-with-mit-license-and-20-point-math-jump"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "DeepSeek"
company_url: "https://alphasignal.ai/company/deepseek_ai"
published: "2026-07-04T02:44:38.000Z"
updated: "2026-07-04T02:54:38.478Z"
type: "Model"
topics:
  - "Llms"
  - "Open Source"
subtopics:
  - "Long Context"
  - "Structured Output"
upvotes: 4282
source_url: "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324"
comments: 0
truncated: true
---

# DeepSeek Quietly Drops V3-0324 With MIT License and 20-Point Math Jump

> DeepSeek quietly drops a major V3 update with near-reasoning-model math scores, MIT license, and 1M+ downloads on Hugging Face

[DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324) landed on Hugging Face with no press release, no blog post, and no fanfare. On March 24, 2025, DeepSeek quietly uploaded a new model checkpoint to public repositories. No formal announcement accompanied the release. The update emerged through community discovery and rapidly circulated through AI development circles. That low-key style is becoming a signature move for a lab that keeps punching above its weight.

The license is MIT, which is new: the previous DeepSeek V3 had a custom license. That alone is a meaningful shift for teams that need permissive terms for commercial deployment. The model has since crossed 1 million downloads on Hugging Face.

## Same bones, sharper brain

The model structure of DeepSeek-V3-0324 is exactly the same as DeepSeek-V3\. What changed is everything under the hood of post-training. While it uses the same base model as DeepSeek-V3, the post-training pipeline has been improved, drawing lessons from the reinforcement learning technique in DeepSeek-R1\. This allows the new model to have better reasoning performance, coding skills, and tool-use capabilities.

The benchmark jumps are hard to ignore:

* **AIME** (competition math): 39.6 → 59.4 (**+19.8 points**)
* **GPQA** (graduate-level science): 59.1 → 68.4 (**+9.3 points**)
* **LiveCodeBench** (real-world coding): 39.2 → 49.2 (**+10.0 points**)
* **MMLU-Pro** (broad knowledge): 75.9 → 81.2 (**+5.3 points**)

In math and coding evaluations, DeepSeek-V3-0324 even outperforms GPT-4.5\. The AIME jump of nearly 20 points is particularly striking for a non-reasoning model, meaning one that does not use extended chain-of-thought at inference time.

## The architecture powering it

DeepSeek-V3 is a Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, it adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures. MoE means the model routes each token through only a small subset of its parameters, keeping compute costs manageable despite the enormous total size.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [DeepSeek-V3-0324 Model Card](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)
- [Simon Willison: DeepSeek-V3-0324](https://simonwillison.net/2025/Mar/24/deepseek/)
- [DeepSeek API Change Log](https://api-docs.deepseek.com/updates)
- [Artificial Analysis: DeepSeek V3 0324 Provider Benchmarks](https://artificialanalysis.ai/models/deepseek-v3-0324/providers)
- [DeepSeek-V3 Technical Report (arXiv)](https://arxiv.org/abs/2412.19437)