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

Can I run Ornith-1.5-122B on an NVIDIA B300?

Yes, just

Its published weights (250 GB) fit in the 259 GB an NVIDIA B300 can use, with room for ≈ 256K tokens of context.

Full analysis of Ornith-1.5-122B Everything that runs on NVIDIA B300 Get the weights on Hugging Face
hf download ornith-ai/Ornith-1.5-122B

Files and context on NVIDIA B300

Each file of Ornith-1.5-122B (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 NVIDIA B300 Context (16-bit)Context (8-bit)
As published250 GBTight256K256K
BF16unsloth/Ornith-1.5-122B-GGUF249 GBTight256K256K
Q8_0unsloth/Ornith-1.5-122B-GGUF133 GBFits256K256K
UD-Q6_K_XLunsloth/Ornith-1.5-122B-GGUF114 GBFits256K256K
UD-Q5_K_XLunsloth/Ornith-1.5-122B-GGUF94.6 GBFits256K256K
UD-Q4_K_XLunsloth/Ornith-1.5-122B-GGUF79.7 GBFits256K256K
UD-Q3_K_XLunsloth/Ornith-1.5-122B-GGUF59.8 GBFits256K256K
UD-IQ3_XXSunsloth/Ornith-1.5-122B-GGUF49.5 GBFits256K256K
UD-Q2_K_XLunsloth/Ornith-1.5-122B-GGUF44.5 GBFits256K256K
UD-IQ2_XXSunsloth/Ornith-1.5-122B-GGUF42.0 GBFits256K256K
UD-IQ1_Munsloth/Ornith-1.5-122B-GGUF40.4 GBFits256K256K
BF16ornith-ai/Ornith-1.5-122B-GGUF249 GBTight256K256K
Q8_0ornith-ai/Ornith-1.5-122B-GGUF133 GBFits256K256K
Q6_Kornith-ai/Ornith-1.5-122B-GGUF102 GBFits256K256K
Q5_K_Mornith-ai/Ornith-1.5-122B-GGUF88.7 GBFits256K256K
Q4_K_Mornith-ai/Ornith-1.5-122B-GGUF75.8 GBFits256K256K

Ornith-1.5-122B on other hardware

Popular models that run on NVIDIA B300

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.