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

Can I run Qwen3-14B on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from Qwen/Qwen3-14B-GGUF (15.7 GB) fits, with room for ≈ 40K tokens of context.

Full analysis of Qwen3-14B Everything that runs on RTX 5090 Get the Q8_0 file on Hugging Face
ollama run hf.co/Qwen/Qwen3-14B-GGUF:Q8_0

Files and context on RTX 5090

Each file of Qwen3-14B (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 5090 Context (16-bit)Context (8-bit)
As published29.5 GBDoesn't fit——
Q8_0Qwen/Qwen3-14B-GGUF15.7 GBFits40K40K
Q6_KQwen/Qwen3-14B-GGUF12.1 GBFits40K40K
Q5_K_MQwen/Qwen3-14B-GGUF10.5 GBFits40K40K
Q5_0Qwen/Qwen3-14B-GGUF10.3 GBFits40K40K
Q4_K_MQwen/Qwen3-14B-GGUF9.00 GBFits40K40K

Qwen3-14B on other hardware

Popular models that run on RTX 5090

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.