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

Can I run Nanbeige_Nanbeige4.3-33B-GGUF on an RTX 5090?

Yes, just

Its Q6_K_S file (27.8 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 5K tokens of context.

Full analysis of Nanbeige_Nanbeige4.3-33B-GGUF Everything that runs on RTX 5090 Get the Q6_K_S file on Hugging Face
ollama run hf.co/bartowski/Nanbeige_Nanbeige4.3-33B-GGUF:Q6_K_S

Files and context on RTX 5090

Each file of Nanbeige_Nanbeige4.3-33B-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 5090 Context (16-bit)Context (8-bit)
BF1666.2 GBDoesn't fit——
Q8_035.2 GBDoesn't fit——
Q6_K_L30.4 GBDoesn't fit——
Q6_K29.0 GBDoesn't fit——
Q6_K_S27.8 GBTight5K10K
Q5_K_M25.1 GBTight17K34K
Q5_K_S23.7 GBTight24K47K
Q4_K_L22.3 GBFits30K59K
Q4_121.2 GBFits35K70K
IQ4_NL20.9 GBFits36K73K
Q4_K_M20.8 GBFits37K73K
Q4_K_S19.7 GBFits42K83K
Q4_019.3 GBFits43K87K
IQ4_XS18.6 GBFits47K93K
IQ3_M17.8 GBFits50K101K
Q3_K_L17.3 GBFits53K106K
Q3_K_M15.9 GBFits59K118K
IQ3_XS15.2 GBFits62K125K
Q3_K_S15.2 GBFits62K125K
IQ3_XXS14.5 GBFits66K131K
Q2_K13.5 GBFits70K140K
IQ2_M12.2 GBFits76K152K
IQ2_S11.2 GBFits81K162K
IQ2_XS10.6 GBFits83K167K
IQ2_XXS10.1 GBFits86K172K

Nanbeige_Nanbeige4.3-33B-GGUF on other hardware

Popular models that run on RTX 5090

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.