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

Can I run Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP on an RTX 4090?

Yes, just

Its published weights (19.3 GB) fit in the 21.6 GB an RTX 4090 can use, with room for ≈ 67K tokens of context.

Full analysis of Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP Everything that runs on RTX 4090 Get the weights on Hugging Face
hf download DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP

Files and context on RTX 4090

Each file of Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP (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)
As published19.3 GBTight67K134K
BF16DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF18.4 GBTight94K187K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-TOOLS-NEO-MAX-MTP-Q8_0DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF10.7 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-NEO-MAX-MTP-Q8_0DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF10.7 GBFits256K256K
Q8_0DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF10.7 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q8_0DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF10.5 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-TOOLS-NEO-MAX-MTP-Q6_KDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF8.76 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-plusIQ-NEO-MAX-MTP-Q6_KDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF8.76 GBFits256K256K
Q6_KDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF8.76 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q6_KDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF8.56 GBFits256K256K
Q5_K_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF7.84 GBFits256K256K
Q5_K_SDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF7.67 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q5_K_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF7.67 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q5_K_SDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF7.51 GBFits256K256K
Q4_K_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.98 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q4_K_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.83 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_NLDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.76 GBFits256K256K
Q4_K_SDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.69 GBFits256K256K
IQ4_NLDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.62 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-Q4_K_SDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.55 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ4_XSDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.53 GBFits256K256K
IQ4_XSDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF6.40 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ3_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF5.72 GBFits256K256K
IQ3_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF5.62 GBFits256K256K
Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-IQ2_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF4.94 GBFits256K256K
IQ2_MDavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF4.94 GBFits256K256K

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP 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.