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

Can I run Ornith-1.0-35B on an RTX 5090?

Yes, with a GGUF version

The published weights are too big, but the Q6_K file from ornith-ai/Ornith-1.0-35B-GGUF (28.5 GB) fits, with room for ≈ 11K tokens of context.

Full analysis of Ornith-1.0-35B Everything that runs on RTX 5090 Get the Q6_K file on Hugging Face
ollama run hf.co/ornith-ai/Ornith-1.0-35B-GGUF:Q6_K

Files and context on RTX 5090

Each file of Ornith-1.0-35B (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)
As published70.2 GBDoesn't fit——
BF16ornith-ai/Ornith-1.0-35B-GGUF69.4 GBDoesn't fit——
Q8_0ornith-ai/Ornith-1.0-35B-GGUF36.9 GBDoesn't fit——
Q6_Kornith-ai/Ornith-1.0-35B-GGUF28.5 GBTight11K21K
Q5_K_Mornith-ai/Ornith-1.0-35B-GGUF24.7 GBTight191K256K
Q4_K_Mornith-ai/Ornith-1.0-35B-GGUF21.2 GBFits256K256K

Ornith-1.0-35B 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.