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

Can I run REDCELL-26B-A4B-OSINT-Cyber-APEX-GGUF on an RTX 3090?

Yes, just

Its REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Balanced file (20.7 GB) fits in the 21.6 GB an RTX 3090 can use, with room for ≈ 6K tokens of context.

Full analysis of REDCELL-26B-A4B-OSINT-Cyber-APEX-GGUF Everything that runs on RTX 3090 Get the REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Balanced file on Hugging Face
ollama run hf.co/terrorswift/REDCELL-26B-A4B-OSINT-Cyber-APEX-GGUF

Files and context on RTX 3090

Each file of REDCELL-26B-A4B-OSINT-Cyber-APEX-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 3090 Context (16-bit)Context (8-bit)
F1650.5 GBDoesn't fit——
Q8_026.9 GBDoesn't fit——
REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Balanced20.7 GBTight6K18K
REDCELL-26B-A4B-OSINT-Cyber-APEX-Balanced20.7 GBTight6K18K
REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Quality19.7 GBTight18K40K
REDCELL-26B-A4B-OSINT-Cyber-APEX-Quality19.7 GBTight18K40K
REDCELL-26B-A4B-OSINT-Cyber-APEX-I-Compact14.7 GBFits78K161K
REDCELL-26B-A4B-OSINT-Cyber-APEX-Compact14.7 GBFits78K161K
REDCELL-26B-A4B-OSINT-Cyber-APEX-Mini12.3 GBFits106K218K

REDCELL-26B-A4B-OSINT-Cyber-APEX-GGUF on other hardware

Popular models that run on RTX 3090

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.