Can I run Clover-35B-A3B-Preview on an RTX 6000 Ada?

Yes, with a GGUF version

The published weights are too big, but the Q8_0 file from Diffuspace/Clover-35B-A3B-Preview-GGUF (37.9 GB) fits, with room for ≈ 128K tokens of context.

Full analysis of Clover-35B-A3B-Preview Everything that runs on RTX 6000 Ada Get the Q8_0 file on Hugging Face

ollama run hf.co/Diffuspace/Clover-35B-A3B-Preview-GGUF:Q8_0

Files and context on RTX 6000 Ada

Each file of Clover-35B-A3B-Preview (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	69.3 GB	Doesn't fit	—	—
Q8_0Diffuspace/Clover-35B-A3B-Preview-GGUF	37.9 GB	Tight	128K	128K
Q4_K_MDiffuspace/Clover-35B-A3B-Preview-GGUF	23.0 GB	Fits	128K	128K
Q4_0Diffuspace/Clover-35B-A3B-Preview-GGUF	19.6 GB	Fits	128K	128K

Clover-35B-A3B-Preview 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.