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

Can I run deepseek-coder-7b-instruct-v1.5 on an RTX 3090?

Yes

Its published weights (13.8 GB) fit in the 21.6 GB an RTX 3090 can use, with room for ≈ 4K tokens of context.

Full analysis of deepseek-coder-7b-instruct-v1.5 Everything that runs on RTX 3090 Get the weights on Hugging Face
hf download deepseek-ai/deepseek-coder-7b-instruct-v1.5

Files and context on RTX 3090

Each file of deepseek-coder-7b-instruct-v1.5 (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 3090 Context (16-bit)Context (8-bit)
As published13.8 GBFits4K4K
4-bit (estimate)3.89 GBFits4K4K

deepseek-coder-7b-instruct-v1.5 on other hardware

Popular models that run on RTX 3090

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.