Can I run K2-Horizon-7B on an RTX 6000 Ada?

Yes

Its published weights (18.0 GB) fit in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 167K tokens of context.

Full analysis of K2-Horizon-7B Everything that runs on RTX 6000 Ada Get the weights on Hugging Face

hf download IFM/K2-Horizon-7B

Files and context on RTX 6000 Ada

Each file of K2-Horizon-7B (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 6000 Ada	Context (16-bit)	Context (8-bit)
As published	18.0 GB	Fits	167K	334K
BF16IFM/K2-Horizon-7B-GGUF	18.0 GB	Fits	167K	334K
Q8_0IFM/K2-Horizon-7B-GGUF	9.57 GB	Fits	223K	445K
Q6_KIFM/K2-Horizon-7B-GGUF	7.39 GB	Fits	237K	474K
Q5_K_MIFM/K2-Horizon-7B-GGUF	6.47 GB	Fits	243K	487K
Q5_0IFM/K2-Horizon-7B-GGUF	6.34 GB	Fits	244K	488K
Q4_K_MIFM/K2-Horizon-7B-GGUF	5.59 GB	Fits	249K	498K

K2-Horizon-7B on other hardware

Popular models that run on RTX 6000 Ada

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.