Can I run humanizer on an RTX 3090?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from jialinyyzz/humanizer-GGUF (12.7 GB) fits, with room for ≈ 62K tokens of context.

Full analysis of humanizer Everything that runs on RTX 3090 Get the Q8_0 file on Hugging Face

ollama run hf.co/jialinyyzz/humanizer-GGUF:Q8_0

Files and context on RTX 3090

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.

File	Size	On RTX 3090	Context (16-bit)	Context (8-bit)
As published	23.9 GB	Doesn't fit	—	—
BF16jialinyyzz/humanizer-GGUF	23.8 GB	Doesn't fit	—	—
Q8_0jialinyyzz/humanizer-GGUF	12.7 GB	Fits	62K	128K
Q6_Kjialinyyzz/humanizer-GGUF	10.0 GB	Fits	81K	167K
Q4_K_Mjialinyyzz/humanizer-GGUF	7.63 GB	Fits	99K	203K
IQ3_XXSjialinyyzz/humanizer-GGUF	5.59 GB	Fits	114K	234K
IQ2_XSjialinyyzz/humanizer-GGUF	3.89 GB	Fits	127K	256K

humanizer on other hardware

Popular models that run on RTX 3090

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.