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

Can I run Qwen3-Coder-30B-A3B-Instruct-FP8 on an RTX 3090?

Probably, at 4-bit

The published weights are too big, but a 4-bit version (about 17.2 GB) would fit, with room for ≈ 44K tokens of context. The site hasn't analyzed a GGUF of Qwen3-Coder-30B-A3B-Instruct-FP8 yet.

Full analysis of Qwen3-Coder-30B-A3B-Instruct-FP8 Everything that runs on RTX 3090

Files and context on RTX 3090

Each file of Qwen3-Coder-30B-A3B-Instruct-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 3090 Context (16-bit)Context (8-bit)
As published31.2 GBDoesn't fit——
4-bit (estimate)17.2 GBFits44K88K

Qwen3-Coder-30B-A3B-Instruct-FP8 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.