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

Can I run Qwen3.5-4B on an RTX 5090?

Yes

Its published weights (9.32 GB) fit in the 28.8 GB an RTX 5090 can use, with room for ≈ 256K tokens of context.

Full analysis of Qwen3.5-4B Everything that runs on RTX 5090 Get the weights on Hugging Face
hf download Qwen/Qwen3.5-4B

Files and context on RTX 5090

Each file of Qwen3.5-4B (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)
As published9.32 GBFits256K256K
BF16unsloth/Qwen3.5-4B-GGUF8.42 GBFits256K256K
UD-Q8_K_XLunsloth/Qwen3.5-4B-GGUF5.95 GBFits256K256K
Q8_0unsloth/Qwen3.5-4B-GGUF4.48 GBFits256K256K
UD-Q6_K_XLunsloth/Qwen3.5-4B-GGUF4.15 GBFits256K256K
Q6_Kunsloth/Qwen3.5-4B-GGUF3.53 GBFits256K256K
UD-Q5_K_XLunsloth/Qwen3.5-4B-GGUF3.25 GBFits256K256K
Q5_K_Munsloth/Qwen3.5-4B-GGUF3.14 GBFits256K256K
Q5_K_Sunsloth/Qwen3.5-4B-GGUF3.02 GBFits256K256K
UD-Q4_K_XLunsloth/Qwen3.5-4B-GGUF2.91 GBFits256K256K
Q4_1unsloth/Qwen3.5-4B-GGUF2.78 GBFits256K256K
Q4_K_Munsloth/Qwen3.5-4B-GGUF2.74 GBFits256K256K
Q4_K_Sunsloth/Qwen3.5-4B-GGUF2.59 GBFits256K256K
Q4_0unsloth/Qwen3.5-4B-GGUF2.58 GBFits256K256K
IQ4_NLunsloth/Qwen3.5-4B-GGUF2.58 GBFits256K256K
IQ4_XSunsloth/Qwen3.5-4B-GGUF2.48 GBFits256K256K
UD-Q3_K_XLunsloth/Qwen3.5-4B-GGUF2.44 GBFits256K256K
Q3_K_Munsloth/Qwen3.5-4B-GGUF2.29 GBFits256K256K
Q3_K_Sunsloth/Qwen3.5-4B-GGUF2.11 GBFits256K256K
UD-IQ3_XXSunsloth/Qwen3.5-4B-GGUF1.95 GBFits256K256K
UD-Q2_K_XLunsloth/Qwen3.5-4B-GGUF1.94 GBFits256K256K
UD-IQ2_Munsloth/Qwen3.5-4B-GGUF1.76 GBFits256K256K
UD-IQ2_XXSunsloth/Qwen3.5-4B-GGUF1.52 GBFits256K256K

Qwen3.5-4B 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.