DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]

Well props to them for continuing to improve, winning on cost-effectiveness, and continuing to publicly share their improvements. Hard not to root for them as a force to prevent an AI corporate monopoly/duopoly.

How will the Google/Anthropic/OpenAI's of the world make money on AI if open models are competitive with their models? What hurt open source in the past was its inability to keep up with the quality and feature depth of closed source competitors, but models seem to be reaching a performance plateau; the top open weight models are generally indistinguishable from the top private models.

Infrastructure owners with access to the cheapest energy will be the long run winners in AI.

Worth noting this is not only good on benchmarks, but significantly more efficient at inference https://x.com/_thomasip/status/1995489087386771851

> DeepSeek-V3.2 introduces significant updates to its chat template compared to prior versions. The primary changes involve a revised format for tool calling and the introduction of a "thinking with tools" capability.

At first, I thought they had gone the route of implementing yet another chat format that can handle more dynamic conversations like that, instead of just using Harmony, but looking at the syntax, doesn't it look exactly like Harmony? That's a good thing, don't get me wrong, but why not mention straight up that they've implemented Harmony, so people can already understand up front that it's compatible with whatever parsing we're using for GPT-OSS?

It's awesome that stuff like this is open source, but even if you have a basement rig with 4 NVIDIA GeForce RTX 5090 graphic cards ($15-20k machine), can it even run with any reasonable context window that isn't like a crawling 10/tps?

Frontier models are far exceeding even the most hardcore consumer hobbyist requirements. This is even further

Benchmarks are super impressive, as usual. Interesting to note in table 3 of the paper (p. 15), DS-Speciale is 1st or 2nd in accuracy in all tests, but has much higher token output (50% more, or 3.5x vs gemini 3 in the codeforces test!).

Why are there so few 32,64,128,256,512 GB models which could run on current consumer hardware? And why is the maximum RAM on Mac studio M4 128 GB??

After using it a couple hours playing around, it is a very solid entry, and very competitive compared with the big US relaeses. I'd say it's better than GLM4.6 and I'm Kimi K2. Looking forward to v4

For anyone that is interested

"create me a svg of a pelican riding on a bicycle"

https://www.svgviewer.dev/s/FhqYdli5

I genuinely do not understand the evaluations of the US AI industry. The chinese models are so close and far cheaper

Note combination of big frontier level model and MIT license.

Can someone kind please ELI5 this paper?

Remember: If it is not peer-reviewed, then it is an ad.

what is the ballpark vram / gpu requirement to run this ?

How capable are these models at tool calling?

3.2-Exp came out in September: this is 3.2, along with a special checkpoint (DeepSeek-V3.2-Speciale) for deep reasoning that they're claiming surpasses GPT-5 and matches Gemini 3.0

https://x.com/deepseek_ai/status/1995452641430651132

I hate that their model ids don't change as they change the underlying model. I'm not sure how you can build on that.

  % curl https://api.deepseek.com/models \          
    -H "Authorization: Bearer ${DEEPSEEK_API_KEY}"  
  {"object":"list","data":[{"id":"deepseek-chat","object":"model","owned_by":"deepseek"},{"id":"deepseek-reasoner","object":"model","owned_by":"deepseek"}]}

Any results on frontier math or arc ?

Disclaimer: I did not test this yet.

I don't want to make big generalizations. But one thing I noticed with chinese models, especially Kimi, is that it does very well on benchmarks, but fails on vibe testing. It feels a little bit over-fitting to the benchmark and less to the use cases.

I hope it's not the same here.

At least, there is no doubt where he is from !

which version are you?

我是DeepSeek最新版本模型！ 如果你想了解具体的版本号信息，我建议你：

    查看官方文档 - DeepSeek官网和文档会有最准确的版本信息

    关注官方公告 - 版本更新通常会在官方渠道公布

    查看应用商店/网页版 - 使用界面通常会显示当前版本

    强大的对话和推理能力

    128K上下文长度

    文件上传处理（图像、文档等）

    联网搜索功能（需手动开启）

    完全免费使用

有什么其他问题我可以帮你解答吗？

Pretty amazing that a relatively small Chinese hedge fund can build AI better than almost anyone.