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

Can I run Ornith-1.5-122B-GGUF on an RTX 6000 Ada?

Yes, just

Its UD-IQ2_XXS file (42.0 GB) fits in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 43K tokens of context. That file is under 3 bits per weight, so expect noticeably lower quality.

Full analysis of Ornith-1.5-122B-GGUF Everything that runs on RTX 6000 Ada Get the UD-IQ2_XXS file on Hugging Face
ollama run hf.co/unsloth/Ornith-1.5-122B-GGUF:UD-IQ2_XXS

Files and context on RTX 6000 Ada

Each file of Ornith-1.5-122B-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.

FileSizeOn RTX 6000 Ada Context (16-bit)Context (8-bit)
BF16249 GBDoesn't fit——
Q8_0133 GBDoesn't fit——
UD-Q6_K_XL114 GBDoesn't fit——
UD-Q5_K_XL94.6 GBDoesn't fit——
UD-Q4_K_XL79.7 GBDoesn't fit——
UD-Q3_K_XL59.8 GBDoesn't fit——
UD-IQ3_XXS49.5 GBDoesn't fit——
UD-Q2_K_XL44.5 GBDoesn't fit——
UD-IQ2_XXS42.0 GBTight43K86K
UD-IQ1_M40.4 GBTight107K214K

Ornith-1.5-122B-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.