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

Can I run Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive on an RTX 5090?

Yes, just

Its Q5_K file (28.0 GB) fits in the 28.8 GB an RTX 5090 can use, with room for ≈ 34K tokens of context.

Full analysis of Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive Everything that runs on RTX 5090 Get the Q5_K file on Hugging Face
ollama run hf.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive:Q5_K

Files and context on RTX 5090

Each file of Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive (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)
Q8_K43.6 GBDoesn't fit——
Q6_K30.6 GBDoesn't fit——
Q5_K28.0 GBTight34K68K
Q4_K23.4 GBTight253K256K
Q4_K_M21.2 GBFits256K256K
IQ4_NL19.8 GBFits256K256K
Q3_K19.0 GBFits256K256K
IQ4_XS18.7 GBFits256K256K
IQ3_M15.4 GBFits256K256K
Q2_K15.0 GBFits256K256K
IQ2_M11.7 GBFits256K256K

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive 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.