Can I run Qwen3.8-3.6-27B-blend on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the Q5_K_M file from JetBrains/Qwen3.8-3.6-27B-blend-GGUF (19.5 GB) fits, with room for ≈ 136K tokens of context.

Full analysis of Qwen3.8-3.6-27B-blend Everything that runs on RTX 5090 Get the Q5_K_M file on Hugging Face

ollama run hf.co/JetBrains/Qwen3.8-3.6-27B-blend-GGUF:Q5_K_M

Files and context on RTX 5090

Each file of Qwen3.8-3.6-27B-blend (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)
As published	55.6 GB	Doesn't fit	—	—
Q5_K_MJetBrains/Qwen3.8-3.6-27B-blend-GGUF	19.5 GB	Fits	136K	256K
Q4_K_MJetBrains/Qwen3.8-3.6-27B-blend-GGUF	16.8 GB	Fits	176K	256K
IQ4_XSJetBrains/Qwen3.8-3.6-27B-blend-GGUF	14.3 GB	Fits	214K	256K
Q3_K_XLJetBrains/Qwen3.8-3.6-27B-blend-GGUF	13.1 GB	Fits	231K	256K
IQ3_SJetBrains/Qwen3.8-3.6-27B-blend-GGUF	12.6 GB	Fits	239K	256K

Qwen3.8-3.6-27B-blend 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.