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

Can I run Qwen2.5-Coder-32B-Instruct-AWQ on an RTX 3060 12 GB?

No

Even its smallest file (As published, 19.3 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 2 of them.

Full analysis of Qwen2.5-Coder-32B-Instruct-AWQ Everything that runs on RTX 3060 12 GB

Files and context on RTX 3060 12 GB

Each file of Qwen2.5-Coder-32B-Instruct-AWQ (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 3060 12 GB Context (16-bit)Context (8-bit)
As published19.3 GBDoesn't fit——

Qwen2.5-Coder-32B-Instruct-AWQ on other hardware

Popular models that run on RTX 3060 12 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.