Can I run Qwen3.8-27B-BaseQuant-V1 on an RTX 5090?

Yes, just

Its Qwen3.8-27B-BaseQuant-V1-XL file (25.3 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 50K tokens of context.

Full analysis of Qwen3.8-27B-BaseQuant-V1 Everything that runs on RTX 5090 Get the Qwen3.8-27B-BaseQuant-V1-XL file on Hugging Face

ollama run hf.co/basecompute/Qwen3.8-27B-BaseQuant-V1

Files and context on RTX 5090

Each file of Qwen3.8-27B-BaseQuant-V1 (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.

File	Size	On RTX 5090	Context (16-bit)	Context (8-bit)
Qwen3.8-27B-BaseQuant-V1-XL	25.3 GB	Tight	50K	100K
Qwen3.8-27B-BaseQuant-V1-Large	20.8 GB	Fits	117K	233K
Qwen3.8-27B-BaseQuant-V1-Medium	16.4 GB	Fits	182K	256K
Qwen3.8-27B-BaseQuant-V1-Small	10.9 GB	Fits	256K	256K
Qwen3.8-27B-BaseQuant-V1-XS	8.36 GB	Fits	256K	256K

Qwen3.8-27B-BaseQuant-V1 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.