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

Can I run Qwen3.5-4B on an RTX 4060?

Yes, with a GGUF version

The published weights are too big, but the UD-Q8_K_XL file from unsloth/Qwen3.5-4B-GGUF (5.95 GB) fits, with room for ≈ 36K tokens of context.

Full analysis of Qwen3.5-4B Everything that runs on RTX 4060 Get the UD-Q8_K_XL file on Hugging Face
ollama run hf.co/unsloth/Qwen3.5-4B-GGUF:UD-Q8_K_XL

Files and context on RTX 4060

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 4060 Context (16-bit)Context (8-bit)
As published9.32 GBDoesn't fit——
BF16unsloth/Qwen3.5-4B-GGUF8.42 GBDoesn't fit——
UD-Q8_K_XLunsloth/Qwen3.5-4B-GGUF5.95 GBTight36K71K
Q8_0unsloth/Qwen3.5-4B-GGUF4.48 GBFits79K159K
UD-Q6_K_XLunsloth/Qwen3.5-4B-GGUF4.15 GBFits89K179K
Q6_Kunsloth/Qwen3.5-4B-GGUF3.53 GBFits108K216K
UD-Q5_K_XLunsloth/Qwen3.5-4B-GGUF3.25 GBFits116K232K
Q5_K_Munsloth/Qwen3.5-4B-GGUF3.14 GBFits119K239K
Q5_K_Sunsloth/Qwen3.5-4B-GGUF3.02 GBFits123K246K
UD-Q4_K_XLunsloth/Qwen3.5-4B-GGUF2.91 GBFits126K253K
Q4_1unsloth/Qwen3.5-4B-GGUF2.78 GBFits130K256K
Q4_K_Munsloth/Qwen3.5-4B-GGUF2.74 GBFits131K256K
Q4_K_Sunsloth/Qwen3.5-4B-GGUF2.59 GBFits136K256K
Q4_0unsloth/Qwen3.5-4B-GGUF2.58 GBFits136K256K
IQ4_NLunsloth/Qwen3.5-4B-GGUF2.58 GBFits136K256K
IQ4_XSunsloth/Qwen3.5-4B-GGUF2.48 GBFits139K256K
UD-Q3_K_XLunsloth/Qwen3.5-4B-GGUF2.44 GBFits140K256K
Q3_K_Munsloth/Qwen3.5-4B-GGUF2.29 GBFits145K256K
Q3_K_Sunsloth/Qwen3.5-4B-GGUF2.11 GBFits150K256K
UD-IQ3_XXSunsloth/Qwen3.5-4B-GGUF1.95 GBFits155K256K
UD-Q2_K_XLunsloth/Qwen3.5-4B-GGUF1.94 GBFits155K256K
UD-IQ2_Munsloth/Qwen3.5-4B-GGUF1.76 GBFits161K256K
UD-IQ2_XXSunsloth/Qwen3.5-4B-GGUF1.52 GBFits168K256K

Qwen3.5-4B on other hardware

Popular models that run on RTX 4060

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.