Can I run Tess-4.5-27B on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the Q6_K file from migtissera/Tess-4.5-27B-GGUF (22.1 GB) fits, with room for ≈ 98K tokens of context.

Full analysis of Tess-4.5-27B Everything that runs on RTX 5090 Get the Q6_K file on Hugging Face

ollama run hf.co/migtissera/Tess-4.5-27B-GGUF:Q6_K

Files and context on RTX 5090

Each file of Tess-4.5-27B (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	—	—
Q8_0migtissera/Tess-4.5-27B-GGUF	28.6 GB	Doesn't fit	767	1K
Q6_Kmigtissera/Tess-4.5-27B-GGUF	22.1 GB	Fits	98K	196K
Q4_K_Mmigtissera/Tess-4.5-27B-GGUF	16.5 GB	Fits	180K	256K

Tess-4.5-27B 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.