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

Can I run Underdog-Saluki-27B-1.0-MTP-GGUF on an RTX 5080?

Yes

Its Underdog-Saluki-27B-1.0-IQ2-mix-MTP file (8.35 GB) fits in the 14.4 GB an RTX 5080 can use, with room for ≈ 88K tokens of context.

Full analysis of Underdog-Saluki-27B-1.0-MTP-GGUF Everything that runs on RTX 5080 Get the Underdog-Saluki-27B-1.0-IQ2-mix-MTP file on Hugging Face
ollama run hf.co/Kujira/Underdog-Saluki-27B-1.0-MTP-GGUF

Files and context on RTX 5080

Each file of Underdog-Saluki-27B-1.0-MTP-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 5080 Context (16-bit)Context (8-bit)
Underdog-Saluki-27B-1.0-IQ2-mix-MTP8.35 GBFits88K176K

Underdog-Saluki-27B-1.0-MTP-GGUF on other hardware

Popular models that run on RTX 5080

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.