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

Can I run Qwen3.5-4B-GGUF on an RTX 4090?

Yes

Its BF16 file (8.42 GB) fits in the 21.6 GB an RTX 4090 can use, with room for ≈ 256K tokens of context.

Full analysis of Qwen3.5-4B-GGUF Everything that runs on RTX 4090 Get the BF16 file on Hugging Face
ollama run hf.co/unsloth/Qwen3.5-4B-GGUF:BF16

Files and context on RTX 4090

Each file of Qwen3.5-4B-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 4090 Context (16-bit)Context (8-bit)
BF168.42 GBFits256K256K
UD-Q8_K_XL5.95 GBFits256K256K
Q8_04.48 GBFits256K256K
UD-Q6_K_XL4.15 GBFits256K256K
Q6_K3.53 GBFits256K256K
UD-Q5_K_XL3.25 GBFits256K256K
Q5_K_M3.14 GBFits256K256K
Q5_K_S3.02 GBFits256K256K
UD-Q4_K_XL2.91 GBFits256K256K
Q4_12.78 GBFits256K256K
Q4_K_M2.74 GBFits256K256K
Q4_K_S2.59 GBFits256K256K
Q4_02.58 GBFits256K256K
IQ4_NL2.58 GBFits256K256K
IQ4_XS2.48 GBFits256K256K
UD-Q3_K_XL2.44 GBFits256K256K
Q3_K_M2.29 GBFits256K256K
Q3_K_S2.11 GBFits256K256K
UD-IQ3_XXS1.95 GBFits256K256K
UD-Q2_K_XL1.94 GBFits256K256K
UD-IQ2_M1.76 GBFits256K256K
UD-IQ2_XXS1.52 GBFits256K256K

Qwen3.5-4B-GGUF on other hardware

Popular models that run on RTX 4090

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.