Model Anatomy See what's inside open-weight AI models

Can I run DeepSeek-R1-Distill-Qwen-7B on an RTX 4090?

Yes

Its published weights (15.2 GB) fit in the 21.6 GB an RTX 4090 can use, with room for ≈ 108K tokens of context.

Full analysis of DeepSeek-R1-Distill-Qwen-7B Everything that runs on RTX 4090 Get the weights on Hugging Face
hf download deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Files and context on RTX 4090

Each file of DeepSeek-R1-Distill-Qwen-7B (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

FileSizeOn RTX 4090 Context (16-bit)Context (8-bit)
As published15.2 GBFits108K128K
4-bit (estimate)4.28 GBFits128K128K

DeepSeek-R1-Distill-Qwen-7B on other hardware

Popular models that run on RTX 4090

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.