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

Can I run Ornith-1.0-9B on an RTX 4060?

Yes, with a GGUF version

The published weights are too big, but the Q5_K_M file from ornith-ai/Ornith-1.0-9B-GGUF (6.47 GB) fits, with room for ≈ 20K tokens of context.

Full analysis of Ornith-1.0-9B Everything that runs on RTX 4060 Get the Q5_K_M file on Hugging Face
ollama run hf.co/ornith-ai/Ornith-1.0-9B-GGUF:Q5_K_M

Files and context on RTX 4060

Each file of Ornith-1.0-9B (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 4060 Context (16-bit)Context (8-bit)
As published18.8 GBDoesn't fit——
BF16ornith-ai/Ornith-1.0-9B-GGUF17.9 GBDoesn't fit——
Q8_0ornith-ai/Ornith-1.0-9B-GGUF9.53 GBDoesn't fit——
Q6_Kornith-ai/Ornith-1.0-9B-GGUF7.36 GBDoesn't fit——
Q5_K_Mornith-ai/Ornith-1.0-9B-GGUF6.47 GBTight20K41K
Q4_K_Mornith-ai/Ornith-1.0-9B-GGUF5.63 GBFits45K91K

Ornith-1.0-9B on other hardware

Popular models that run on RTX 4060

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.