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

Can I run DeepSeek-Coder-V2-Lite-Instruct on an RTX 5060 Ti 16 GB?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 8.83 GB) would fit, with room for ≈ 160K tokens of context. The site hasn't analyzed a GGUF of DeepSeek-Coder-V2-Lite-Instruct yet.

Full analysis of DeepSeek-Coder-V2-Lite-Instruct Everything that runs on RTX 5060 Ti 16 GB

Files and context on RTX 5060 Ti 16 GB

Each file of DeepSeek-Coder-V2-Lite-Instruct (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 5060 Ti 16 GB Context (16-bit)Context (8-bit)
As published31.4 GBDoesn't fit——
4-bit (estimate)8.83 GBFits160K160K

DeepSeek-Coder-V2-Lite-Instruct on other hardware

Popular models that run on RTX 5060 Ti 16 GB

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.