DeepSeek-V4-Pro-0813: hardware requirements
DeepSeek-V4-Pro-0813 needs about 1786 GB of memory at Published quantization: a 1782 GB download plus room for context and a runtime allowance. That is beyond consumer hardware; use it through an API instead.
Will it run on your machine?
Use it without your own hardware
OpenRouter lists DeepSeek V4 Pro 0813 at $0.66 per million input tokens and $1.98 per million output tokens.
Price as listed on OpenRouter today. Speed is for hosted servers, not a home computer.
Download sizes by quantization
Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?
| Quant | Download | RAM @ 4K | RAM @ 32K | Source |
|---|---|---|---|---|
| Published | 1782 GB | 1786 GB | 1789 GB | deepseek-ai/DeepSeek-V4-Pro-0813 |
Download sizes are measured from the published files named in the Source column. The RAM columns add the context cache, calculated from the model's configuration, and a runtime allowance of 10% of the download (at least 0.5GB, at most 3GB).