Can I run Kolibri-1-GGUF on an RTX 6000 Ada?

Yes, just

Its Q3_K_M file (37.5 GB) fits in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 256K tokens of context.

Full analysis of Kolibri-1-GGUF Everything that runs on RTX 6000 Ada Get the Q3_K_M file on Hugging Face

ollama run hf.co/Hob-forge/Kolibri-1-GGUF:Q3_K_M

Files and context on RTX 6000 Ada

Each file of Kolibri-1-GGUF (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)
Q8_0	83.1 GB	Doesn't fit	—	—
Q6_K	64.2 GB	Doesn't fit	—	—
Q5_K_M	55.6 GB	Doesn't fit	—	—
Q4_K_M	47.5 GB	Doesn't fit	—	—
Q3_K_M	37.5 GB	Tight	256K	256K
Q2_K	28.6 GB	Fits	256K	256K

Kolibri-1-GGUF 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.