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

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

Chinese AI lab DeepSeek’s last model release was V3.2 (and V3.2 Speciale) last December. They just dropped the first of their hotly anticipated V4 series in the shape of two preview models, DeepSeek-V4-Pro and DeepSeek-V4-Flash.

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.

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).

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 possible the Pro model may run on it if I can stream just the necessary active experts from disk.

For the moment I tried the models out via OpenRouter, using llm-openrouter:

llm install llm-openrouter llm openrouter refresh llm -m openrouter/deepseek/deepseek-v4-pro 'Generate an SVG of a pelican riding a bicycle'

Here’s the pelican for DeepSeek-V4-Flash:

And for DeepSeek-V4-Pro:

For comparison, take a look at the pelicans I got from DeepSeek V3.2 in December, V3.1 in August, and V3-0324 in March 2025.

... continue reading