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

Can I run Groot-19B-A3B-261023 on an RTX 5060 Ti 16 GB?

Yes, with a GGUF version

The published weights are too big, but the Q4_K_M file from GrootTeam/Groot-19B-A3B-261023-GGUF (11.7 GB) fits, with room for ≈ 128K tokens of context.

Full analysis of Groot-19B-A3B-261023 Everything that runs on RTX 5060 Ti 16 GB Get the Q4_K_M file on Hugging Face
ollama run hf.co/GrootTeam/Groot-19B-A3B-261023-GGUF:Q4_K_M

Files and context on RTX 5060 Ti 16 GB

Each file of Groot-19B-A3B-261023 (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 5060 Ti 16 GB Context (16-bit)Context (8-bit)
As published38.9 GBDoesn't fit——
Q4_K_MGrootTeam/Groot-19B-A3B-261023-GGUF11.7 GBTight128K255K

Groot-19B-A3B-261023 on other hardware

Popular models that run on RTX 5060 Ti 16 GB

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.