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

Can I run Qwen3-Coder-Next-FP8 on an RTX 3060 12 GB?

No

Even its smallest file (4-bit (estimate), 44.8 GB) is more than an RTX 3060 12 GB can hold (10.8 GB usable): it needs 5 of them.

Full analysis of Qwen3-Coder-Next-FP8 Everything that runs on RTX 3060 12 GB

Files and context on RTX 3060 12 GB

Each file of Qwen3-Coder-Next-FP8 (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 published80.4 GBDoesn't fit——
4-bit (estimate)44.8 GBDoesn't fit——

Qwen3-Coder-Next-FP8 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.