DeepSeek V4 Flash

Runs on your device

DeepSeek · Jul 2026

DeepSeek's V4 Flash - a 284B mixture-of-experts with 13B active per token and a 1M-token context. Frontier-class reasoning and agentic work on a workstation with a big graphics card and 128 GB or more of main memory.

Context
1M tokens
Smallest download
96.9 GB
Runs from
128 GB RAM
License
MIT
reasoningagenticcodingmathlong contextanalysis

Will DeepSeek V4 Flash run on your machine?

This is the same sizing the app uses - not a marketing estimate.

284B-A13B (MoE)96.9 GB downloadToo big for this machine
284B-A13B (MoE)137.9 GB downloadToo big for this machine

On Apple Silicon, system memory is also graphics memory - pick "None / integrated / Apple Silicon" and read the bars against your Mac's memory. The app checks your real hardware before every download.

Variants & sizes

VariantDownloadQuantizationNeedsApple Silicon
284B-A13B (MoE)MoE96.9 GBUD-Q2_K_XL128 GB RAMMetal (GGUF)
284B-A13B (MoE)MoE137.9 GBUD-IQ4_XS192 GB RAMMetal (GGUF)

The app picks the right variant for your machine and verifies every download. Model files come straight from their official repositories, pinned to exact revisions.

License

DeepSeek V4 Flash is released under the MIT - read the terms. The weights download to your machine and stay there; Your Own AI adds no accounts, tracking, or lock-in on top.

Frequently asked questions

Can I run DeepSeek V4 Flash offline?
Yes. DeepSeek V4 Flash is a downloadable model: with Your Own AI it runs entirely on your computer, works with no internet connection, and your conversations never leave your device.
What hardware does DeepSeek V4 Flash need?
The smallest variant (284B-A13B (MoE), a 96.9 GB download) runs on a machine with 128 GB of memory. Larger variants want more memory or a graphics card - the interactive checker on this page grades every variant against your hardware, using the same logic as the app.
Is DeepSeek V4 Flash free to use?
The model weights are released under the MIT license and download at no charge. Your Own AI itself is free and open source for local use.
How much context does DeepSeek V4 Flash support?
1M tokens of context.

Run DeepSeek V4 Flash in two clicks

Download Your Own AI, pick DeepSeek V4 Flash, and the app sizes it to your hardware. Private by architecture - no account needed for local use.