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

Can I run humanizer on an RTX 4060?

Yes, with a GGUF version

The published weights are too big, but the IQ3_XXS file from jialinyyzz/humanizer-GGUF (5.59 GB) fits, with room for ≈ 7K tokens of context.

Full analysis of humanizer Everything that runs on RTX 4060 Get the IQ3_XXS file on Hugging Face
ollama run hf.co/jialinyyzz/humanizer-GGUF:IQ3_XXS

Files and context on RTX 4060

Each file of humanizer (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 published23.9 GBDoesn't fit——
BF16jialinyyzz/humanizer-GGUF23.8 GBDoesn't fit——
Q8_0jialinyyzz/humanizer-GGUF12.7 GBDoesn't fit——
Q6_Kjialinyyzz/humanizer-GGUF10.0 GBDoesn't fit——
Q4_K_Mjialinyyzz/humanizer-GGUF7.63 GBDoesn't fit——
IQ3_XXSjialinyyzz/humanizer-GGUF5.59 GBFits7K19K
IQ2_XSjialinyyzz/humanizer-GGUF3.89 GBFits20K44K

humanizer 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.