DeepSeek V4 - almost on the frontier, a fraction of the price

Simon Willison ·

DeepSeek released V4-Pro (1.6T params, 49B active) and V4-Flash (284B params, 13B active) as their first V4 preview models—1M token context MoE architectures under MIT license, with Pro claiming the title of largest open weights model.

Categories: Model Releases, OSS & Tools

Excerpt

<p>Chinese AI lab DeepSeek's last model release was V3.2 (and V3.2 Speciale) <a href="https://simonwillison.net/2025/Dec/1/deepseek-v32/">last December</a>. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro">DeepSeek-V4-Pro</a> and <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash">DeepSeek-V4-Flash</a>.</p> <p>Both models are 1 million token context Mixture of Experts. Pro is 1.6T total parameters, 49B active. Flash is 284B total, 13B active. They're using the standard MIT license.</p> <p>I think this makes DeepSeek-V4-Pro the new largest open weights model. It's larger than Kimi K2.6 (1.1T) and GLM-5.1 (754B) and more than twice the size of DeepSeek V3.2 (685B).</p> <p>Pro is 865GB on Hugging Face, Flash is 160GB. I'm hoping that a lightly quantized Flash will run on my 128GB M5 MacBook Pro. It's <em>possible</em> the Pro model may run on it if I can stream just the necessary active experts from disk.</p> <p>For the moment I tried the models out via <a href="https://openrouter.ai/">OpenRouter</a>, using <a href="https://github.com/simonw/llm-openrouter">llm-openrouter</a>:</p> <pre><code>llm install llm-openrouter llm openrouter refresh llm -m openrouter/deepseek/deepseek-v4-pro 'Generate an SVG of a pelican riding a bicycle' </code></pre> <p>Here's the pelican <a href="https://gist.github.com/simonw/4a7a9e75b666a58a0cf81495acddf529">for DeepSeek-V4-Flash</a>:</p> <p><img alt="Excellent bicycle - good frame shape, nice chain, even has a reflector on the front wheel. Pelican has a mean looking expression but has its wings on the handlebars and feet on the pedals. Pouch is a little sharp." src="https://static.simonwillison.net/static/2026/deepseek-v4-flash.png" /></p> <p>And <a href="https://gist.github.com/simonw/9e8dfed68933ab752c9cf27a03250a7c">for DeepSeek-V4-Pro</a>:</p> <p><img alt="Another solid bicycle, albeit the spokes are a little jag

Read at source: https://simonwillison.net/2026/Apr/24/deepseek-v4/#atom-everything

Discussions