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

Can I run Qwen3.8-27B-QSA-GGUF on an RTX 5090?

Yes

Its UD-Q6_K file (22.2 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 96K tokens of context.

Full analysis of Qwen3.8-27B-QSA-GGUF Everything that runs on RTX 5090 Get the UD-Q6_K file on Hugging Face
ollama run hf.co/higa2515/Qwen3.8-27B-QSA-GGUF:UD-Q6_K

Files and context on RTX 5090

Each file of Qwen3.8-27B-QSA-GGUF (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)
Q8_029.3 GBDoesn't fit——
UD-Q6_K22.2 GBFits96K192K
UD-Q5_K_M20.0 GBFits129K256K
UD-Q4_K_M16.7 GBFits178K256K

Qwen3.8-27B-QSA-GGUF 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.