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

Can I run Winnow-12B on an RTX 5070 Ti?

Yes, just

Its Q8_0 file (12.7 GB) fits in the 14.4 GB an RTX 5070 Ti can use, with room for ≈ 8K tokens of context.

Full analysis of Winnow-12B Everything that runs on RTX 5070 Ti Get the Q8_0 file on Hugging Face
ollama run hf.co/EldanRing/Winnow-12B:Q8_0

Files and context on RTX 5070 Ti

Each file of Winnow-12B (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 5070 Ti Context (16-bit)Context (8-bit)
Winnow-12B-BF1623.8 GBDoesn't fit——
Q8_012.7 GBTight8K21K
Winnow-12B-NVFP48.16 GBFits41K88K

Winnow-12B on other hardware

Popular models that run on RTX 5070 Ti

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.