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

Can I run Swift-1.5-Flash-Next-Heretic-ReverseEngineer on an RTX PRO 6000 Blackwell?

Yes, just

Its IQ3_S file (84.6 GB) fits in the 86.4 GB an RTX PRO 6000 Blackwell can use, with room for ≈ 67K tokens of context.

Full analysis of Swift-1.5-Flash-Next-Heretic-ReverseEngineer Everything that runs on RTX PRO 6000 Blackwell Get the IQ3_S file on Hugging Face
llama-server -hf trubisky/Swift-1.5-Flash-Next-Heretic-ReverseEngineer:IQ3_S

Files and context on RTX PRO 6000 Blackwell

Each file of Swift-1.5-Flash-Next-Heretic-ReverseEngineer (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 PRO 6000 Blackwell Context (16-bit)Context (8-bit)
IQ4_NL109 GBDoesn't fit——
IQ4_XS94.7 GBDoesn't fit——
IQ3_S84.6 GBTight67K135K

Swift-1.5-Flash-Next-Heretic-ReverseEngineer on other hardware

Popular models that run on RTX PRO 6000 Blackwell

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.